BibTeX Entry

author = {Takaki Makino and Yousuke Niwa and Ayumu Nagai},

title = {Efficient implementation of Fast Fourier Transformation on {AP}-1000+},

note = {Winner of the 3rd Parallel Software Contest, held by the Joint Symposium on Parallel Processing (Talk at Waseda University International Conference Center)},

year = 1996,

month = jun

author = {Takaki Makino},

title = {Implementation of an Efficient Feature Structure Abstract Machine},

howpublished = {A Senior thesis, Department of Information Science, the University of Tokyo},

year = 1997,

ps = {makino1997a.ps.gz},

abstract = {This study focuses on an implementation of a feature structure abstract machine, a framework for handling feature structures efficiently, whose basic notion was proposed by Carpenter et al. The feature structures, which are usually represented as directed graphs or terms in logic programming language, are compiled into an instruction sequence of the abstract machine. High-efficiency is accomplished since an interpretative process of feature structures can be omitted. In addition to the implementation, this study pursues several extensions of the instruction set and the compilation method in the original framework. Comparison with other systems is also shown.}

title = {Feature Structure Abstract Machine and Realization of Partial Unification},

author = {Takaki Makino and Kenji Nishida and Kentaro Torisawa and {Jun-ichi} Tsujii},

year = 1997,

booktitle = {Proceedings of the 3rd Annual Meeting of the {A}ssociation for {N}atural {L}anguage {P}rocessing},

pages = {193$\,$--$\,$196},

address = {Kyoto, Japan},

note = {(In Japanese)},

pdf = {makino1997b.pdf}

author = {Takaki Makino and Kentaro Torisawa and {Jun-ichi} Tsujii},

title = {{LiLFeS} --- Practical Programming Language For Typed Feature Structures},

pages = {239$\,$--$\,$244},

booktitle = {Proceedings of the 4th {N}atural {L}anguage {P}rocessing {P}acific {Rim} {S}ymposium},

year = 1997,

address = {Phuket, Thailand},

ps = {makino1997c.ps.gz},

abstract = {This paper describes LiLFeS, an integrated unification-based programming system for linguistic formalisms based on typed feature structures, such as HPSG. The core engine of LiLFeS is an abstract machine developed for efficient handling of typed feature structures. Its basic design and optimization techniques are described. Performance comparisons between LiLFeS and other systems for typed feature structures show that LiLFeS is more than 50 times faster than ALE, and competitive to ProFIT.}

author = {Nishida, Kenji and Makino, Takaki and Torisawa, Kentaro and Tateisi, Yuka and Tsujii, {Jun-ichi}},

title = {Extension of a Feature Structure Abstract Machine for Partial Unification},

booktitle = {Proceedings of the Conference of {P}acific {A}ssociation for {C}omputational {L}inguistics ({PACLING} '97)},

pages = {232$\,$--$\,$243},

year = 1997,

address = {Ohme, Japan},

ps = {nishida97.ps.gz},

abstract = { This paper describes an extension of a feature structure abstract machine for supporting partial unification, which is used in an efficient parsing algorithm for HPSG proposed by Torisawa et al. An abstract machine for attribute-value logics, a framework for processing typed feature structures proposed by Carpenter and Qu, is not only efficient but also easily extendable. We extended the abstract machine for partial unification by only adding a set of instructions to the machine. By combining this technique with the pre-computation of possible feature structures, efficiency of HPSG parsing is improved. We also show the feasibility of our implementation by a series of experiments. }

author = {Yuka Tateisi and Kentaro Torisawa and Takaki Makino and Kenji Nishida and Masachika Fuchigami and {Jun-ichi} Tsujii},

title = {Conversion of {LTAG} English Grammar to {HPSG}},

booktitle = {IPSJ SIG notes NL-122},

pages = {119$\,$--$\,$126},

year = 1997,

ps = {tateisi1997.ps.gz},

note = {(In Japanese)}

title = {{LiLFeS} --- Towards a Practical {HPSG} Parser},

author = {Takaki Makino and Minoru Yoshida and Kentaro Torisawa and {Jun-ichi} Tsujii},

year = 1998,

booktitle = {Proceedings of the 17th {I}nternational {C}onference on {C}omputational {L}inguistics and the 36th {A}nnual {M}eeting of the {A}ssociation for {C}omputational {L}inguistics},

pages = {807$\,$--$\,$811},

address = {Montreal, Canada},

ps = {makino1998.ps.gz},

abstract = {This paper presents the LiLFeS system, an efficient feature-structure description language for HPSG. The core engine of LiLFeS is an Abstract Machine for Attribute-Value Logics, proposed by Carpenter and Qu. Basic design policies, the current status, and performance evaluation of the LiLFeS system are described. The paper discusses two implementations of the LiLFeS. The first one is based on an emulator of the abstract machine, while the second one uses a native-code compiler and therefore is much more efficient than the first one.}

author = {Minoru Yoshida and Takaki Makino and Kentaro Torisawa and {Jun-ichi} Tsujii},

title = {Optimization Techniques for a Feature Structure Processing Language {LiLFeS}},

booktitle = {Proceedings of the 4th Annual Meeting of the {A}ssociation for {N}atural {L}anguage {P}rocessing},

year = {1998},

address = {Fukuoka, Japan},

pages = {93$\,$--$\,$96},

note = {(in Japanese)}

author = {Kentaro Torisawa and Takaki Makino and Minoru Yoshida and Takashi Ninomiya and Kenji Nishida and Hideo Imai and Yutaka Mitsuishi and Hiroshi Kanayama and Yuka Tateisi and Yusuke Miyao and {Jun-ichi} Tsujii},

year = 1999,

title = {Practical {HPSG} Parsers.},

booktitle = {Proceedings of {JSPS} Annual Symposium on Intelligent Information and Advanced Information Processing},

pages = {46$\,$--$\,$50},

ps = {jsps99-hpsg.ps.gz}

author = {Kazama, {Jun-ichi} and Mitsuishi, Yutaka and Makino, Takaki and Torisawa, Kentaro and Matsuda, Kouichi and Tsujii, {Jun-ichi}},

title = {Japanese Morphorogy Analysis for Chatting},

booktitle = {Proceedings of the 5th Annual Meeting of the {A}ssociation for {N}atural {L}anguage {P}rocessing},

year = {1999},

address = {Tokyo},

pages = {509$\,$--$\,$512},

ps = {kazama_nlp99.ps.gz},

pdf = {kazama_nlp99.pdf},

note = {(In Japanese)}

author = {Sadamasa, Kunihiko and Makino, Takaki and Mitsuishi, Yutaka and Torisawa, Kentaro and Matsuda, Kouichi and Tsujii, {Jun-ichi}},

title = {Personal Agent Natural Language Interface ({PANLI}) development toolkit},

booktitle = {Proceedings of the 5th Annual Meeting of the {A}ssociation for {N}atural {L}anguage {P}rocessing},

year = {1999},

address = {Tokyo},

pages = {393$\,$--$\,$396},

note = {(In Japanese)}

author = {Takaki Makino},

title = {A Native-Code Compiler for a Unification-Based Programming Language with Typed Feature Structures},

school = {Department of Information Science, Graduate School of Science, University of Tokyo},

address = {Tokyo, Japan},

year = 1999,

ps = {makino1999.ps.gz},

abstract = { This study discusses design and implementation of a native-code compiler for LiLFeS, a unification-based programming language with typed feature structures (TFSs). Although LiLFeS has been designed as a platform for natural language processing of TFS-based formalisms based on an Abstract Machine for Attribute-Value Logics (AMAVL) proposed by Carpenter et al., people require more efficiency in order to implement advanced natural language processing applications, such as for statistical learning from large corpora. A large number of studies have been made on efficient implementations of Prolog, such as for the native-code compiler Aquarius Prolog, and those studies are partially applicable to the LiLFeS implementation. However, in order to increase efficiency of TFS unification, optimization using type information is necessary and the compiler should directly generate unification code, including type manipulation. A simple extension of current Prolog or AMAVL implementations cannot achieve that. This thesis describes a design for a LiLFeS compiler, which is an extension of the Berkeley Abstract Machine, the implementation framework of Aquarius Prolog. The thesis focuses on an implementation of TFS unification on an abstract machine, including (1) construction and analysis of unification algorithm for direct generation of TFS unification code, (2) design of abstract machine instructions for expressing the algorithm described in (1), and (3) static analysis techniques for type hierarchies and definite clause programs for providing context information used in code optimization. Performance comparisons of the LiLFeS compiler to other LiLFeS and Prolog systems show the high efficiency of the implementation detailed in this thesis. }

author = {Yoshida, Minoru and Takashi Ninomiya and Kentaro Torisawa and Takaki Makino and {Jun'ichi} Tsujii},

year = 1999,

title = {Efficient {FB-LTAG} Parser and its Parallelization},

booktitle = {Proceedings of the Pacific Association for Computational Linguistics (PACLING) '99},

address = {Waterloo, Canada},

pages = {90$\,$--$\,$103},

pdf = {http://www-tsujii.is.s.u-tokyo.ac.jp/%7Emino/pacling99.pdf}

author = {Yusuke Miyao and Takaki Makino and Kentaro Torisawa and {Jun-ichi} Tsujii},

title = {The {LiLFeS} abstract machine and its evaluation with the {LinGO} grammar},

journal = {Natural Language Engineering},

editor = {Flickinger, Dan and Oepen, Stephan and Tsujii, {Jun-ichi} and Uszkoreit, Hans},

volume = 6,

number = 1,

note = {({S}pecial Issue on Efficient Processing with {HPSG})},

pages = {47$\,$--$\,$61},

year = 2000,

ps = {miyao2000.ps.gz},

abstract = { This article evaluates the efficiency of the LiLFeS abstract machine by performing parsing tasks with the LinGO English resource grammar. The instruction set of the abstract machine is optimized for efficient processing of definite clause programs and typed feature structures. LiLFeS also supports various tools required for efficient parsing (e.g. efficient copying, a built-in CFG parser) and the constructions of standard Prolog (e.g. cut, assertions, negation as failure). Several parsers and large-scale grammars, including the LinGO grammar, have been implemented in or ported to LiLFeS. Precise empirical results with the LinGO grammar are provided to allow comparison with other systems. The experimental results demonstrate the efficiency of the LiLFeS abstract machine. }

author = {Makino, Takaki},

title = {Pulse Neural Networks for Language Understanding},

howpublished = {Student Meetings of Speech, Language, and Communication Society in University of Tokyo},

note = {``Well, this study might happen to change the world'' award},

year = 2001,

month = sep

author = {Makino, Takaki and Aihara, Kazuyuki and Tsujii, {Jun-ichi}},

year = {2001},

title = {Towards Sentence Understanding: Phase Arbitration in Temporal-Coding Memory Mechanism},

booktitle = {Proceedings of the Second Workshop on Natural Language Processing and Neural Networks (NLPNN'2001)},

pages = {46$\,$--$\,$52},

address = {Tokyo, Japan},

pdf = {makino2001.pdf},

abstract = {This paper explores a mechanism of memory in human brain from a viewpoint of sentence understanding. We pointed out the following: (1) Some complexity must be incorporated into memory coding in order to be capable of representing binding in a meaning of a sentence. (2) When temporal coding is used to achieve the complexity, some mechanism is required to arbitrate phases (temporal slots) among memorized items. (3) Considering its implementation, the mechanism is likely to be global, which resembles a sort of structured memory, such as a push-down stack. (4) Episodic memory, which is thought to be formed through mammal hippocampus, can be regarded as a phase arbitration mechanism and is possibly related in depth to sentence understanding. }

author = {Makino, Takaki},

title = {A Pulsed Neural Network for Language Understanding: Discrete-Event Simulation of a Short-Term Memory Mechanism and Sentence Understanding},

school = {Department of Information Science, Graduate School of Science, Tokyo University},

type = {{Ph.D.} Dissertation},

address = {Tokyo, Japan},

month = dec,

year = 2001,

abstract = {Various language processing algorithms have been studied to find the algorithm used in the human language understanding, but no algorithm has proven its existence by physiological evidences. In such a situation, we should consider an approach to pursue implementational constraints and preferences from a computational theory of the language understanding process. \par In this paper, we study the model of a short-term memory mechanism of the human brain suitable for language understanding. Specifically, the following three topics are pursued. \par \par (1) The exploration of the element necessary for building a short-term memory mechanism suitable for language understanding in the framework of neural network \par (2) The techniques for an efficient simulation of general pulse neural networks in a continuous time. \par (3) Construction of a primitive simulation of language understanding based on (1) and (2). \par In (1), we clarify the following on the language-understanding neural networks. i) A binding problem has to be solved in order to represent a result of language understanding, and the most promising way is to utilize behavior in the time domain of a neural network. ii) Requirement of phase arbitration causes us to build a structural time-series memory on a neural network. iii) Application of grammatical rules can be implemented in the same way as a prediction of a time series. \par In (2), we studied the event-driven pulse neural network simulator. In order to research complex operations in a time domain, such as phase mediation, the network simulation with high time precision is demanded, while conventional discrete-time systems is limited in simulation speed. On the other hand, discrete-event systems have difficulty in handling delayed firing for general neuron models. In this study, we show that our new technique with the second-order incremental partitioning method enables us to build an event-driven pulse network simulator in general neuron models by numerical calculation of delayed firing times. We also describe technique for more efficient handling of delayed firing by filtering redundant predictions. \par Finally, in (3), we build a neural network simulation model, which understands the simple sentence of 3 to 4 words, in order to demonstrate the studies of language understandings in (1) and (2). We discuss our language-understanding system in various aspects and future directions of research for better understanding of a sentence. },

pdf = {makino2002a.pdf},

ps = {makino2002a.ps.gz}

author = {Araki, Junko and Takashi Ninomiya and Takaki Makino and {Jun'ichi} Tsujii},

title = {Action Vectors for Interpreting Route Descriptions},

booktitle = {Proceedings of the AAAI-02 Workshop on Spatial and Temporal Reasoning},

ps = {http://www-tsujii.is.s.u-tokyo.ac.jp/papers/jun3-aaai2002workshop.ps},

year = {2002}

author = {Araki, Junko and Takashi Ninomiya and Takaki Makino and {Jun'ichi} Tsujii},

title = {Two Perspective systems Using a Route as a Reference Object},

booktitle = {Proceedings of the sixth World Multiconference on Systemics, Cybernetics and Informatics ({SCI} 2002)},

ps = {http://www-tsujii.is.s.u-tokyo.ac.jp/papers/jun3-sci2002.ps},

year = {2002}

author = {Kazama, {Jun'ichi} and Takaki Makino and Yoshihiro Ohta and {Jun'ichi} Tsujii},

title = {Tuning Support Vector Machines for Biomedical Named Entity Recognition},

booktitle = {Proceedings of the ACL-02 Workshop on Natural Language Processing in the Biomedical Domain},

year = {2002},

volume = 3,

month = {July},

address = {Philadelphia, PA, USA},

ps = {http://www-tsujii.is.s.u-tokyo.ac.jp/%7Ekazama/papers/kazama_aclbio02.ps},

pdf = {http://www-tsujii.is.s.u-tokyo.ac.jp/%7Ekazama/papers/kazama_aclbio02.pdf}

author = {Ninomiya, Takashi and Makino, Takaki and Tsujii, Jun'ichi},

year = 2002,

month = oct,

title = {An Indexing Scheme for Typed Feature Structures},

booktitle = {Proceedings of the 19th {I}nternational {C}onference on {C}omputational {L}inguistics},

address = {Taipei, Taiwan},

ps = {coling2002-ninomi-b.ps.gz},

pdf = {coling2002-ninomi-b.pdf},

abstract = {This paper describes an indexing substrate for typed feature structures (ISTFS), which is an efficient retrieval engine for typed feature structures. Given a set of typed feature structures, the ISTFS efficiently retrieves its subset whose elements are unifiable or in a subsumption relation with a query feature structure. The efficiency of the ISTFS is achieved by calculating a unifiability checking table prior to retrieval and finding the best index paths dynamically.}

author = {Makino, Takaki and Aihara, Kazuyuki},

year = 2002,

month = sep,

title = {Impact of Computational Theory of Language Understanding for Development of Neural Network Model},

booktitle = {Proceedings of the 12th conference of {J}apan {N}eural {N}etwork {S}ociety},

address = {Tottori},

pdf = {jnns2002.pdf},

abstract = {},

note = {Received 2002 Promotion Award of Japan Neural Network Society.}

author = {Takaki Makino and Yusuke Miyao and Kentaro Torisawa and {Jun-ichi} Tsujii},

title = {Native-Code Compilation of Feature Structures},

booktitle = {Collaborative Language Engineering: A Case Study in Efficient Grammar-based Processing},

publisher = {{CSLI} Publications},

address = {Stanford, {CA}},

editor = {Oepen, Stephan and Flickinger, Dan and Tsujii, {Jun-ichi} and Uszkoreit, Hans},

year = 2003,

pdf = {makino2000.pdf},

ps = {makino2000.ps.gz}

author = {Makino, Takaki and Aihara, Kazuyuki},

title = {Hypothesis of Brain Processing on Time Stream and Language},

year = 2003,

month = jan,

note = {Presented by poster in the 3rd winter workshop of the Mechanism of the Brain and Mind, Hokkaido, Japan. In Japanese.},

abstract = {}

author = {Makino, Takaki and Aihara, Kazuyuki},

title = {Self-organizing map constructed by synaptic time-dependent plasticity},

year = 2003,

month = aug,

note = {Presented by poster in the 4th summer workshop of the Mechanism of the Brain and Mind, Niigata, Japan. In Japanese.},

pdf = {poster2003.pdf},

abstract = {}

author = {Takaki Makino},

title = {A Discrete-Event Neural Network Simulator for General Neuron Models},

journal = {Neural Computing \& Applications},

year = 2003,

volume = 11,

pages = {210--223},

pdf = {nca2003.pdf},

publisher = {Springer-Verlag London},

abstract = {Efficient simulation techniques for a discrete-event pulsed neural network simulator were developed. In a discrete-event simulation framework, simulation of complex neural behaviors, such as phase precession and phase arbitration, demands prediction of delayed firing times. The new technique, the incremental partitioning method, uses linear envelopes of the state variable of a neuron to partition the simulated time so that the delayed-firing time is reliably calculated by applying the bisection-combined Newton-Raphson method to every partition. The quick filtering technique is also proposed for reducing calculation cost of linear envelopes. The developed simulator, \textsc{Punnets}, has achieved efficiency and precision but still is capable of simulating a complex behavior of large-scale neural network models.}

title = {Self-observation Principle for Estimating the Other's Internal State -- A new computational theory of communication},

author = {Takaki Makino and Kazuyuki Aihara},

type = {Mathematical Engineering Technical Reports},

institution = {Department of Mathematical Informatics, Graduate School of Information Science and Technology, the University of Tokyo},

number = {METR 2003--36},

year = 2003,

month = oct,

pdf = {METR03-36e.pdf},

note = {\url{METR03-36e.pdf}{Revised version (based on comments from an English native) (.pdf)} and \url{METR03-36j.pdf}{Unofficial Japanese version (.pdf)} is also available in addition to the \url{METR03-36.pdf}{original version (.pdf)}},

abstract = {We propose a computational theory of internal-state estimation for others, which is the basis of information processing in human communication. To estimate internal states of the other equivalent to the self, we have to deal with two substantial difficulties, restriction of the estimator's parameter dimension and conversion between objective and subjective information. The proposed computational theory that solves both difficulties is based on \textit{self-observation principle}. Learning the dynamics of the self provides prior knowledge of the dynamics of the other, which reduces the restriction of the parameter dimension; learning the association between the subjective state for the self and the objective observation of the self provides a mechanism for conversion between objective observation of the other and subjective information to the other. In this paper, we formalize communication in a framework of dynamics-estimation problems, and describe the two difficulties and our proposal on the framework. We also discuss relations of our proposal to evolutional psychology and neuroscience.}

author = {Makino, Takaki and Aihara, Kazuyuki},

year = 2004,

month = mar,

title = {Self-observation Principle for Estimating Peers' Internal State -- New Computational Theory on Communication},

booktitle = {Proceedings of the 2nd international symposium on emergent mechanism of communication in the brain},

address = {Awaji-shima, Hyogo},

pdf = {makino2004awaji.pdf}

author = {Makino, Takaki and Jianfeng Feng},

year = 2004,

month = nov,

title = {Configuring Spiking Neural Networks for Given Spatio-Temporal Patterns},

booktitle = {Proceedings of 2004 International Workshop on Biologically Inspired Computing},

address = {Sendai, Miyagi}

title = {Cooperative behavior of agents that model the other and the self in noisy iterated Prisoners' Dilemma simulation},

author = {Makino, Takaki and Aihara, Kazuyuki},

booktitle = {Proceedings of 2005 4th IEEE International Conference on Development and Learning (ICDL'05)},

year = {2005},

pages = {52-57}

author = {Makino, Takaki and Aihara, Kazuyuki},

title = {The Self-observation Principle and Iterated Prisoners' Dilemma},

year = 2005,

month = jan,

note = {Presented by poster in the 5th winter workshop of the Mechanism of the Brain and Mind, Hokkaido, Japan. In Japanese.},

abstract = {}

author = {Makino, Takaki and Hirayama, Kotaro and Aihara, Kazuyuki},

title = {Understanding others: Possible links among parity, mirror neurons, and communication},

year = 2005,

note = {(Supplemental commentary to the article ``From monkey-like action recognition to human language: An evolutionary framework for neurolinguistics'' by Michael A. Arbib) http://www.bbsonline.org/Preprints/Arbib-05012002/Supplemental/},

journal = {Behavioral Brain \& Sciences},

abstract = {In the target article, LR3 (Parity), one of the possible criteria for language readiness, is defined with a simple description: ``What counts for the speaker (or producer) must count for the listener (or receiver).'' Based on a self-observation principle, we would like to suggest that this ability plays a much more crucial role in communication than can be inferred from the statement, namely, the role of ``understanding others.''}

author = {Makino, Takaki and Aihara, Kazuyuki},

year = 2006,

title = {Multi-agent Reinforcement Learning Algorithm to Handle Beliefs of Other Agents' Policies and Embedded Beliefs},

booktitle = {Proceedings of the 5th International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS'06)},

pages = {789--791},

month = may,

address = {Hakodate, Hokkaido},

pdf = {makino2006multiagent.pdf},

abstract = {We have developed a new series of multi-agent reinforcement learning algorithms that choose a policy based on beliefs about co-players’policies. The algorithms are applicable to situations where a state is fully observable by the agents, but there is no limit on the number of players. Some of the algorithms employ embedded beliefs to handle the cases that co-players are also choosing a policy based on their beliefs of others’ policies. Simulation experiments on Iterated Prisoners’ Dilemma games show that the algorithms using on policy-based belief converge to highly mutually-cooperative behavior, unlike the existing algorithms based on action-based belief.}

title = {Theoretical Model and Simulation Study for Mutual Understanding of Others},

author = {Takaki Makino and Kazuyuki Aihara},

booktitle = {Proc. of the Joint Conference of Welfare, Wellbeing, and Life Support},

volume = {5},

pages = 33,

year = 2007,

note = {In Japanese}

author = {Makino, Takaki and Aihara, Kazuyuki},

title = {Simulating Others},

journal = {Journal of The Japan Society for Simulation Technology},

note = {In Japanese},

volume = 26,

year = 2007,

pages = {171--175},

abstract = {We briefly describe \textit{mentalizing}, or understanding others' mental states, in an active research area of cognitive science. To overcome inaccessiblity of others' mental states, theoretical studies assume some mentalizing mechanism in the brain, including simulating others' behavior within knowledge of behavior of the self. We also present our computer-simulation study that tackles the role of mentalizing in a social environment, which examines behavior of agents based on reinforcement learning in Iterated Prisoners' Dilemma games. The results show that agents that choose actions using the estimated policy (corresponding to the mental state) of the co-player, achieve higher cooperation rates than control agents do, which choose actions using only the expected action of the co-player, or only the recent history of game plays. }

title = {Investigation on Usefulness of Functional Brain Imaging Data in Designated Hospitals for Inpatient Care},

booktitle = {FY2007 Summary and Member Report of the Study on Monitoring for Improving Expert Treatment with Medical Treatment and Supervision Act},

author = {Fukui, Hiroki and Kawada, Ryosaku and Sano, Masataka and Takahashi, Yoko and Taruya, Toshihiro and Nishinaka, Hirofumi and Makino, Takaki and Masuda, Naohisa and Morisaki, Yohei},

year = {2008},

pages = {83--84},

note = {In Japanese}

author = {Makino, Takaki},

title = {Failure, instead of inhibition, should be monitored for the distinction of self/other and actual/possible actions},

journal = {Behavioral and Brain Sciences},

year = 2008,

volume = 31,

number = 1,

pages = {32--33},

publisher = {Cambridge University Press},

address = {New York, NY, USA},

note = {A commentary for Susan Hurley's article ``The Shared Circuits Model: How Control, Mirroring and Simulation Can Enable Imitation, Deliberation, and Mindreading''.},

abstract = {I suggest that layer 4 of the shared circuits model (SCM) should monitor the failure of performing an action, instead of output inhibition, to obtain actual/possible and self/other distinction. The target article's assumption of selective inhibition leaves some questions unansweres, such asa the criteria for the selection. Monitoing failure can answer these questions because failure does not require selection. It also provices a basis for more likely explanation for the phylogenetic and ontogenetic origin of both monitoring and output inhibition.}

author = {Yukiko Mino and Takayuki Okada and Akiko Kikuchi and Takaki Makino and Kazuo Yoshikawa},

title = {Status and Issues in Inpatient Treatment under Mental Health Welfare Act during Outpatient Treatment under Medical Care and Treatment Act -- Monitoring Investigation on Designated Outpatient Treatment Institutes},

journal = {Shihou Seishin Igaku (Forensic Mental Health)},

year = {2008},

volume = 4,

number = 1,

pages = {111},

note = {In Japanese}

author = {Takaki Makino},

title = {Automatic Acquisition of {TD}-Network in {POMDP} Environments: Extension with {SRN} structure},

booktitle = {Oral presentation at the 22nd Annual Conference of the Japanese Society for Artificial Intelligence},

year = {2008},

month = jun,

abstract = {We propose a new neural network architecture, Simple recurrent TD Networks (SR-TDNs), that learns to predict future observations in partially observable environments, using proto-predictive representation of states. SR-TDNs incorporate the structure of simple recurrent neural networks (SRNs) into temporal-difference (TD) networks to use proto-predictive representation of states. Our simulation experiments revealed that these networks have better on-line learning capacity than TD networks in various environments.},

pdf = {100183.pdf}

author = {Takaki Makino and Kazuyuki Aihara},

title = {Self-observation Principle: Mathematical Framework of Recognizing Others},

booktitle = {Oral presentation at the 22nd Annual Conference of the Japanese Society for Artificial Intelligence},

year = {2008},

month = jun,

note = {In Japanese},

abstract = {We briefly describe \textit{mentalizing}, or understanding others' mental states, in an active research area of cognitive science. To overcome inaccessiblity of others' mental states, theoretical studies assume some mentalizing mechanism in the brain, including simulating others' behavior within knowledge of behavior of the self. We also present our computer-simulation study that tackles the role of mentalizing in a social environment, which examines behavior of agents based on reinforcement learning in Iterated Prisoners' Dilemma games. The results show that agents that choose actions using the estimated policy (corresponding to the mental state) of the co-player, achieve higher cooperation rates than control agents do, which choose actions using only the expected action of the co-player, or only the recent history of game plays.},

pdf = {100181.pdf}

author = {Makino, Takaki and Takagi, Toshihisa},

title = {On-line Discovery of Temporal-Difference Networks},

booktitle = {ICML '08: Proceedings of the 25th Annual International Conference on Machine Learning},

year = 2008,

publisher = {Omnipress},

location = {Helsinki, Finland},

editor = {Andrew McCallum and Sam Roweis},

pages = {632--639},

abstract = {We present an algorithm for on-line, incremental discovery of temporal-difference (TD) networks. The key contribution is the establishment of three criteria to expand a node in TD network: a node is expanded when the node is well-known, independent, and has a prediction error that requires further explanation. Since none of these criteria requires centralized calculation operations, they are easily computed in a parallel and distributed manner, and scalable for bigger problems compared to other discovery methods of predictive state representations. Through computer experiments, we demonstrate the empirical effectiveness of our algorithm.},

pdf = {Makino2008ICML.pdf}

author = {Taiki Takahashi and Takaki Makino and Yu Ohmura and Hiroki Fukui},

title = {Employing delay and probability discounting frameworks for a neuroeconomic understanding of gambling behavior},

editor = {M. J. Esposito},

booktitle = {Psychology of Gambling},

pages = {67--82},

publisher = {Nova Science},

year = {2008}

author = {Takaki Makino and Taiki Takahashi and Hiroki Fukui},

title = {Modeling Decision Mechanism as a Reinforcement Learning with Probabilistic Discounting},

booktitle = {Proceedings of the 2nd WFSBP Asia-Pacific Congress},

year = {2008},

volume = 30,

pages = 157,

month = sep

author = {Mino, Yukiko and Makino, Takaki and Miyamoto, Masami},

title = {Attitude Survey for Staffs at Designated Inpatient Institutions for Medical Observation Act},

year = {2008},

journal = {Japanese Psychiatric Nursing Society},

address = {Tokyo},

volume = 51,

number = 3,

pages = {490--494},

note = {In Japanese}

author = {Shiro, Masanori and Makino, Takaki and Aihara, Kazuyuki},

title = {Investigation on Information Separation using Integrate-and-Fire Neuron Model},

booktitle = {Oral presentation at the 22nd Annual Conference of the Japanese Society for Artificial Intelligence},

location = {Asahikawa},

year = {2008},

month = jun,

note = {In Japanese},

pdf = {100327.pdf}

author = {Akada, Yohei and Makino, Takaki and Takagi, Toshihisa},

title = {A Mechanism of Rule Abstraction Through Interaction With Environment},

booktitle = {Oral presentation at the 22nd Annual Conference of the Japanese Society for Artificial Intelligence},

location = {Asahikawa},

year = {2008},

month = jun,

note = {In Japanese},

pdf = {100184.pdf}

author = {Shiro, Masanori and Makino, Takaki and Aihara, Kazuyuki},

title = {Anticipating Non-linear Information Using Liquid State Machine},

booktitle = {Proc. of the 9th Summer Workshop on the Mechanism of Brain and Mind},

location = {Sapporo},

year = {2008},

month = aug,

note = {In Japanese}

author = {Shiro, Masanori and Makino, Takaki and Aihara, Kazuyuki},

title = {Prediction on Non-linear Temporal Sequence using Liquid State Machine Model},

booktitle = {Oral Presentation at the 18th National Conference of Japanese Neural Network Society},

location = {Tsukuba},

year = {2008},

month = sep,

note = {In Japanese},

pdf = {P1-25.pdf}

author = {Makino, Takaki},

title = {Simple Recurrent Temporal-Difference Networks},

year = {2008},

month = oct,

booktitle = {Presented in Workshop on Information-Based Induction Sciences (IBIS2008)},

location = {Sendai}

author = {Akiya, Kanemitsu and Makino, Takaki and Kraines, Steven and Takagi, Toshihisa},

title = {Extracting various binary relations from biomedical papers using natural language processing techniques and ontology},

booktitle = {Proceedings of the 15th Annual Meeting of the {A}ssociation for {N}atural {L}anguage {P}rocessing},

location = {Tottori},

year = {2009},

month = mar

author = {Takaki Makino and Taiki Takahashi and Hiroki Fukui},

title = {Psychopathic Tendency and Decision Mechanism in the Brain: Description with Reinforcement Learning Model},

journal = {Shihou Seishin Igaku (Forensic Mental Health)},

year = {2009},

volume = 4,

number = 1,

pages = {115-116},

note = {In Japanese}

author = {Makino, Takaki and Takahashi, Taiki and Nishinaka, Hirofumi and Fukui, Hiroki},

title = {Correlation Analysis between Cognitions and Actions under Probabilistic Discounting Model},

booktitle = {Proc. of the 48th Conference of Japanese Society for Medical and Biological Engineering},

location = {Tokyo},

year = {2009},

month = apr,

note = {In Japanese}

author = {Makino, Takaki and Takahashi, Taiki and Nishinaka, Hirofumi and Fukui, Hiroki},

title = {Correlation Analysis of Cognitive Probabilistic Discounting for {I}owa Gambling Task Action Selection},

booktitle = {Proc. of the 31st conference on Japanese Society of Biological Psychiatry},

location = {Kyoto},

month = apr,

volume = 31,

pages = 179,

year = {2009},

note = {In Japanese}

author = {Makino, Takaki},

title = {Proto-Predictive Representation of States with Simple Recurrent Temporal-Difference Networks},

booktitle = {ICML '09: Proceedings of the 26th Annual international conference on machine learning},

year = 2009,

editor = {L\'{e}on Bottou and Michael Littman},

publisher = {Omnipress},

address = {Montreal},

pages = {697--704},

abstract = {We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable environments. SR-TDNs incorporate the structure of simple recurrent neural networks (SRNs) into temporal-difference (TD) networks to use proto-predictive representation of states. Although they deviate from the principle of predictive representations to ground state representations on observations, they follow the same learning strategy as TD networks, i.e., applying TD-learning to general predictions. Simulation experiments revealed that SR-TDNs can correctly represent states with incomplete set of core tests (question networks), and consequently, SR-TDNs have better on-line learning capacity than TD networks in various environments.},

month = jun,

pdf = {Makino2009ICML.pdf}

author = {Takaki Makino and Taiki Takahashi and Hirofumi Nishinaka and Hiroki Fukui},

title = {Probabilistic Discounting for Modeling Behaviors in {I}owa Gambling Task},

booktitle = {Proceedings of Multi-disciplinary Symposium on Reinforcement Learning (MSRL 2009)},

year = 2009,

month = jun,

location = {Montreal}

author = {Mino, Yukiko and Okada, Takayuki and Kikuchi, Akiko and Sano, Masataka and Makino, Takaki and Yoshikawa, Kazuo},

title = {Monitoring Study for Improving Specialized Treatments in Designated Inpatient Institutions},

journal = {Japanese Psychiatric Nursing Society},

volume = 52,

number = 2,

pages = {233--237},

year = {2009},

note = {In Japanese}

author = {Takaki Makino},

title = {Self-organization of Commucation},

booktitle = {Handbook of Self-organization},

publisher = {NTS Pub},

year = {2009},

note = {In Japanese},

editors = {国武 豊喜 他},

pages = {438--443}

author = {Makino, Takaki},

month = oct,

title = {Hierarchical State Infinite Hidden Markov Model},

year = {2009},

howpublished = {Poster Presentation at Workshop on Information-Based Induction Sciences 2009 (IBIS2009)}

author = {Takei, Shunsuke and Makino, Takaki and Takagi, Toshihisa},

title = { Split Position Slice Sampler},

booktitle = {Technical Report on Information-Based Induction Sciences 2009 (IBIS2009)},

month = oct,

year = {2009},

pdf = {ibistakei.pdf},

abstract = {We propose a new tree sampling algorithm for Bayesian probabilistic con-text-free grammar (PCFG) called Split Position Slice Sampler. Split Position Slice Sampler is developed based on Beam Sampling method that is a fast MCMC sam-pling algorithm for Bayesian Hidden Markov Model, and adapted to Bayesian PCFG. This tree sampling method can be combined with Metropolis-Hastings sam-pler to constitute an efficient grammar sampling algorithm for Bayesian PCFG. Be-cause this algorithm does not involve any approximation, more efficient inference is achieved without losing accuracy. We evaluate our approach by comparing with an existing method in a small artificial corpus.},

location = {Fukuoka},

note = {In Japanese}

author = {Takaki Makino and Shunsuke Takei and Daichi Mochihashi and Issei Sato and Toshihisa Takagi},

month = dec,

title = {Conditional Simultaneous Draws from Hierarchical {Chinese} Restaurant Processes},

year = {2009},

howpublished = {Poster Presentation at Nonparametric Bayes Workshop at NIPS 2009 (NPBayes2009)}

title = {Cultural neuroeconomics of intertemporal choice.},

author = {Takahashi, Taiki and Hadzibeganovic, Tarik and Cannas, Sergio A. and Makino, Takaki and Fukui, Hiroki and Kitayama, Shinobu},

volume = 30,

number = 2,

year = 2009,

pages = {185--191},

journal = {Neuroendocrinology Letters},

abstract = {According to theories of cultural neuroscience, Westerners and Easterners may have distinct styles of cognition (e.g., different allocation of attention). Previous research has shown that Westerners and Easterners tend to utilize analytical and holistic cognitive styles, respectively. On the other hand, little is known regarding the cultural differences in neuroeconomic behavior. For instance, economic decisions may be affected by cultural differences in neurocomputational processing underlying attention; however, this area of neuroeconomics has been largely understudied. In the present paper, we attempt to bridge this gap by considering the links between the theory of cultural neuroscience and neuroeconomic theory of the role of attention in intertemporal choice. We predict that (i) Westerners are more impulsive and inconsistent in intertemporal choice in comparison to Easterners, and (ii) Westerners more steeply discount delayed monetary losses than Easterners. We examine these predictions by utilizing a novel temporal discounting model based on Tsallis’ statistics (i.e. a q-exponential model). Our preliminary analysis of temporal discounting of gains and losses by Americans and Japanese confirmed the predictions from the cultural neuroeconomic theory. Future study directions, employing computational modeling via neural networks, are briefly outlined and discussed.},

pdf = {http://www.famaf.unc.edu.ar/~cannas/papers/paper56.pdf}

author = {Nishinaka, Hirofumi and Takahashi, Taiki and Makino, Takaki and Fukui, Hiroki},

title = {Study on Nearsitedness in Psychopathic Tendency},

booktitle = {Proceedings of the 5th Annual Conference of Japanese Association of Forensic Mental Health},

journal = {Shihou Seishin Igaku (Forensic Mental Health)},

volume = 5,

number = 1,

page = 132,

year = 2010,

note = {5th Annual Conference of Japanese Association of Forensic Mental Health (May 2009), In Japanese}

author = {Nishinaka, Hirofumi and Takahashi, Taiki and Makino, Takaki and Fukui, Hiroki},

title = {Decisions under psychopayhic tendency: investigation from neuroeconomics},

booktitle = {Proceedings of the 31th Conference of Japanese Society of Biological Psychiatry},

year = {2009},

vollume = 31,

pages = 174,

month = jun,

note = {In Japanese}

title = {Study on Monitoring Designated Outpatient Institutes: Focusing on Estimate of Outpatient Treatment Duration and Analysis on Combined Use of Admission by Mental Health and Welfare Act},

author = {Yukiko Mino and Kumiko Ando and Takayuki Okada and Akiko Kikuchi and Masataka Sano and Takaki Makino and Kazuo Yoshikawa},

volume = 39,

number = 1,

year = 2010,

month = jan,

pages = {93--100},

journal = {Clinical Psychiatry},

note = {In Japanese}

author = {Takaki Makino},

title = {Nonparametric {B}ayesian Estimation for Hidden {M}arkov Model and {MCMC} Method},

howpublished = {Invited talk at the workshop of Markov chain Monte Carlo method and its surroundings (Institute of Statistical Mathematics)},

year = 2010,

month = feb

author = {Takaki Makino},

title = {Hierarchical state clustering of hidden {M}arkov models with hierarchical {D}irichlet processes},

howpublished = {Invited talk at the Keihanna Talk (Keihanna research center, NICT)},

year = 2010,

month = apr

author = {Takaki Makino and Hisao Taki and Kazuyuki Aihara},

title = {Altruistic behavior and recursive estimation of others' internal states},

journal = {Seisan-Kenkyu},

volume = 62,

number = 3,

pages = {259--265},

year = 2010,

month = may,

note = {In Japanese}

author = {Takaki Makino},

title = {Conference Report of {ICML} 2009},

journal = {Journal of Japan Artificial Intelligence Society},

volume = 25,

number = 3,

pages = {459--460},

year = 2010,

note = {In Japanese}

author = {Takaki Makino},

title = {Statistical Machine Learning Based on Nonparametric Bayesian Models},

type = {IEICE Technical Report},

number = {IBISML2010-14},

institution = {Institute of Electronics, Information and Communication Engineers},

year = 2010,

month = jun,

pages = {87--94},

note = {In Japanese}

title = {Bridging the Knowledge Gap between Research and Education through Textbooks},

author = {Steven Kraines and Takaki Makino and Weisen Guo and Haruo Mizutani and Toshihisa Takagi},

year = {2010},

booktitle = {Advances in Web-Based Learning - ICWL 2010 : 9th International Conference, China, Proceedings},

series = {Lecture Notes in Computer Science},

volume = 6483,

pages = {121-130},

publisher = {Springer}

title = {Slice Sampling for {Chinese} Restaurant Process},

author = {Takaki Makino},

year = {2010},

booktitle = {Proc. of the 2nd Asian Conference on Machine Learning (ACML 2010)}

title = {Current status and issues in treatment and care of mentally disordered offender in designated outpatient hospitals: on difficulties found by multi-disciplinary team staffs},

author = {Yukiko Mino and Takaki Makino and Masami Miyamoto},

volume = 6,

number = 1,

year = 2011,

pages = {2--9},

journal = {Forensic Psychiatry},

note = {In Japanese}

author = {Takaki Makino},

title = {Reinforcement Learning (My Bookmark)},

journal = {Journal of Japan Artificial Intelligence Society},

volume = 26,

number = 3,

pages = {301--303},

year = 2011,

url = {http://www.ai-gakkai.or.jp/jsai/journal/mybookmark/26-3.html}

author = {Sainbayar Sukhbaatar and Takaki Makino and Kazuyuki Aihara and Takashi Chikayama},

title = {Robust Generation of Dynamical Patterns in Human Motion by a Deep Belief Net},

journal = {Journal of Machine Learning Research - Proceedings Track},

volume = {20},

year = {2011},

pages = {231--246},

url = {http://jmlr.csail.mit.edu/proceedings/papers/v20/sukhbaatar11/sukhbaatar11.pdf},

note = {Presented in the 3rd Asian Conference on Machine Learning (ACML 2011)},

location = {Taoyuan, Taiwan},

optinfo = { Accept rate = 38.3\% (23/60)}

author = {Mai Ohguro and Takaki Makino and Ryo Fujie and Kazuyuki Aihara},

title = {Personal Control Strategy in a Three-person Game with Indirect Information},

howpublished = {Presented at Inauguration Symposirum of Meiji Institute for Advanced Study of Mathematical Sciences},

year = 2011,

month = oct

author = {Yuka Yamazaki and Takaki Makino and Ryo Fujie and Kazuyuki Aihara},

title = {Evolutionary Game Based on Similarity of Preference among Neighbor Agents: Simulation of Unification and Schism},

howpublished = {Presented at Inauguration Symposirum of Meiji Institute for Advanced Study of Mathematical Sciences},

year = 2011,

month = oct

title = {{MMPI}-2 Restructured Clinical Scales and {MMPI}-2 Restructured Form},

author = {Yukiko Mino and Takaki Makino and Shota Kasai and Tohru Oguchi},

booktitle = {Proc. of the 75th Annual Convention of Japanese Psychological Association},

year = 2011,

pages = {2PM005},

month = sep,

note = {In Japanese}

title = {College Maladjustment Scale in Supplementary Scales features of {MMPI}-2},

author = {Shota Kasai and Yukiko Mino and Takaki Makino and Tohru Oguchi},

booktitle = {Proc. of the 75th Annual Convention of Japanese Psychological Association},

year = 2011,

pages = {2PM004},

month = sep,

note = {In Japanese}

title = {Addiction Scales ({APS},{AAS}) in Supplementary Scales of {MMPI}-2},

author = {Tohru Oguchi and Yukiko Mino and Shota Kasai and Takaki Makino and Yoshio Otani},

booktitle = {Proc. of the 75th Annual Convention of Japanese Psychological Association},

year = 2011,

pages = {2PM003},

month = sep,

note = {In Japanese}

author = {Takaki Makino and Kazuyuki Aihara},

title = {A Simulation Environment for Mutual Estimation of Peers' Internal State},

booktitle = {Proc. of the 1st International Symposium on Innovative Mathematical Modeling},

year = 2011

author = {Takaki Makino and Haruo Mizutani and Jun Kozuka and Issei Sato},

title = {Beam Hardening Reduction by X-ray CT Reconstruction with Bayesian Inference},

month = nov,

year = {2011},

howpublished = {Poster Presentation at Information-Based Induction Sciences Workshop (IBIS2011)}

author = {Takaki Makino and Shunsuke Takei and Issei Sato and Daichi Mochihashi},

title = {Restricted Collapsed Draw: Accurate Sampling for Hierarchical {C}hinese Restaurant Process Hidden {M}arkov Models},

journal = {arXiv preprint arXiv:1106.0474},

url = {http://arxiv.org/abs/1106.0474},

year = 2011

author = {Jun Kozuka and Takaki Makino and Haruo Mizutani},

title = {Image Reconstruction Device and Program},

year = {2013},

month = {01},

day = {10},

number = {JP-A-2013-5840},

type = {Japan Patent},

version = {},

location = {Japan},

yearfiled = {2011},

monthfiled = {06},

dayfiled = {22},

author = {Hirotaka Hachiya and Tetsuro Morimura and Takaki Makino and Masashi Sugiyama},

title = {Modified {N}ewton Approach to Policy Search},

booktitle = {IEICE Tech. Rep.},

volume = {111},

number = {275},

series = {IBISML2011-54},

pages = {79-85},

address = {Nara},

month = nov,

year = {2011},

note = {Wed, Nov 9, 2011 - Fri, Nov 11 : Nara Womens Univ. (IBISML)}

author = {Takaki Makino and Johane Takeuchi},

title = {Apprenticeship Learning for Model Parameters of Partially Observable Environments},

month = mar,

journal = {Technical Reports of IEICE},

volume = {111},

number = {480},

note = {IBISML2011-94},

pages = {49--54},

publisher = {IEICE},

url = {http://www.ieice.org/ken/paper/2012031290QR/},

year = 2012,

day = 12

author = {Takaki Makino and Chiyori Urabe and Kazuyuki Aihara},

title = {Applicability of {C}onley-{M}orse graphs to Controlled and Noisy Dynamical Systems},

howpublished = {Presented in the 4th Developers Workshop on the Conley-Morse Database Project, Kauai, Hawaii},

year = 2012,

month = mar,

day = 24

author = {Chiyori Urabe and Takaki Makino and Kazuyuki Aihara},

title = {On noisy dynamical systems: logistic maps and quasi-periodically forced systems},

howpublished = {Presented in the 4th Developers Workshop on the Conley-Morse Database Project, Kauai, Hawaii},

year = 2012,

month = mar,

day = 24

author = {Takaki Makino and Johane Takeuchi},

title = {Learning Model Parameters of Partially Observable Markov Decision Process from Demonstration},

booktitle = {Proc. of the 2nd International Symposium on Innovative Mathematical Modeling},

month = may,

pages = 68,

year = 2012

author = {Sainbayar Sukhbaatar and Takaki Makino and Kazuyuki Aihara and Takashi Chikayama},

title = {Robust generation of dynamical patterns in human motion by a deep belief net},

booktitle = {Proc. of the 2nd International Symposium on Innovative Mathematical Modeling},

month = may,

year = 2012

author = {Taichi Kiwaki and Takaki Makino and Kazuyuki Aihara},

title = {A heuristic algorithm for finding the simplest expression of the structure in data},

booktitle = {Proc. of the 2nd International Symposium on Innovative Mathematical Modeling},

month = may,

pages = 109,

year = 2012

author = {Rie Suzuki and Hao San and Masao Hotta and Takaki Makino},

title = {Robust cyclic {ADC} based on $\beta$-expansion},

booktitle = {Proc. of the 2nd International Symposium on Innovative Mathematical Modeling},

month = may,

pages = 116,

year = 2012

author = {Takaki Makino and Johane Takeuchi},

title = {Apprenticeship Learning for Model Parameters of Partially Observable Environments},

booktitle = {ICML '12: Proceedings of the 29th Annual international conference on machine learning},

year = 2012,

abstract = {We consider apprenticeship learning --- i.e., having an agent learn a task by observing an expert demonstrating the task --- in a partially observable environment when the model of the environment is uncertain. This setting is useful in applications where the explicit modeling of the environment is difficult, such as a dialogue system. We show that we can extract information about the environment model by inferring action selection process behind the demonstration, under the assumption that the expert is choosing optimal actions based on knowledge of the true model of the target environment. Proposed algorithms can achieve more accurate estimates of POMDP parameters and better policies from a short demonstration, compared to methods that learns only from the reaction from the environment.},

month = jun,

day = 1,

url = {http://icml.cc/2012/papers/747.pdf}

author = {Takaki Makino and Johane Takeuchi},

title = {Apprenticeship Learning for Model Parameters of Partially Observable Environments},

howpublished = {Poster presentation in EWRL10: the 10th European Workshop on Reinforcement Learning},

year = 2012,

month = jul,

day = 1

title = {Correlation of Psychopathic Deviate Scale ({Pd}) with content and supplementary scales in {MMPI}-2},

author = {Yukiko Mino and Takaki Makino and Shota Kasai},

booktitle = {Proc. of the 76th Annual Convention of Japanese Psychological Association},

year = 2012,

month = sep,

pages = {1AMD06},

note = {In Japanese}

title = {Correlation between {OBS} and Other Basic/Content Scales of {MMPI}-2 with Special Reference to {Pt}},

author = {Shota Kasai and Yukiko Mino and Takaki Makino},

booktitle = {Proc. of the 76th Annual Convention of Japanese Psychological Association},

year = 2012,

month = sep,

pages = {1AMD05},

note = {In Japanese}

title = {Clinical Scale for Psychopathic Deviate in {MMPI}-2 {R}estructured {Form}},

author = {Takaki Makino and Shota Kasai and Yukiko Mino},

booktitle = {Proc. of the 76th Annual Convention of Japanese Psychological Association},

year = 2012,

month = sep,

pages = {1AMD07},

note = {In Japanese}

title = {Software Development and Testing for Machine Learning Studies: With an Example of Probabilistic Inference with {M}onte {C}arlo Based Methods},

author = {Takaki Makino and Kazuyuki Aihara},

journal = {Transactions of the Japanese Society for Artificial Intelligence},

volume = 27,

number = 4,

pages = {253--262},

year = 2012,

month = jul,

url = {http://dx.doi.org/10.1527/tjsai.27.253},

opturl = {http://joi.jlc.jst.go.jp/JST.JSTAGE/tjsai/27.253?lang=en},

abstract = {It is not easy to test software used in studies of machine learning with statistical frameworks. In particular, software for randomized algorithms such as Monte Carlo methods compromises testing process. Combined with underestimation of the importance of software testing in academic fields, many software programs without appropriate validation are being used and causing problems. In this article, we discuss the importance of writing test codes for software used in research, and present a practical way for testing, focusing on programs using Monte Carlo methods.},

note = {In Japanese}

author = {Takaki Makino},

title = {Mathematical Model of Communication with Machine Learning Approach},

howpublished = {Information Science and Technology Application Program Special Talk (Invited Talk by Creative Informatics, Graduate School of Information Science and Technology, the University of Tokyo)},

year = 2012,

month = apr

author = {Hitoshi Matsuo and Takaki Makino},

title = {Auto-Colorization of Monochrome Image Using Object Recognition and {Markov} Random Field},

journal = {IEICE Technical Report},

volume = 112,

numer = 279,

month = nov,

year = {2012},

pages = {351-358},

note = {Presented in Information-Based Induction Sciences Workshop 2012 (IBISML2012-83), In Japanese}

author = {Taichi Kiwaki and Takaki Makino and Kazuyuki Aihara},

title = {Regularization of Restricted {Boltzmann} Machine Learning through Entropy Minimization},

journal = {IEICE Technical Report},

volume = 112,

numer = 279,

month = nov,

year = {2012},

pages = {103-106},

note = {Presented in Information-Based Induction Sciences Workshop 2012 (IBISML2012-48), In Japanese}

author = {Takaki Makino and Yasushi Oda and Kazuyuki Aihara},

title = {Efficient Re-calculation Method and Gradient Computation for {POMDP} Policies},

month = nov,

year = {2011},

howpublished = {Poster Presentation at Information-Based Induction Sciences Workshop (IBIS2012)}

title = {An Experimental Comparison of Quantum Decision Theoretical Models of Intertemporal Choice for Gain and Loss},

author = {Takahashi, Taiki and Nishinaka, Hiroshi and Makino, Takaki and Han, Ruokang and Fukui, Hiroki},

journal = {Journal of Quantum Information Science},

volume = {2},

number = {04},

pages = {119},

year = {2012},

publisher = {Scientific Research Publishing},

url = {https://www.researchgate.net/publication/272667123_An_Experimental_Comparison_of_Quantum_Decision_Theoretical_Models_of_Intertemporal_Choice_for_Gain_and_Loss}

title = {Auto-pooling: Learning to Improve Invariance of Image Features from Image Sequences},

author = {Sainbayar Sukhbaatar and Takaki Makino and Kazuyuki Aihara},

journal = {arXiv preprint arxiv:1301.3323},

year = {2013},

url = {https://arxiv.org/abs/1301.3323}

author = {Takaki Makino and Yukiko Iwata and Yutaka Jitsumatsu and Masao Hotta and Hao San and Kazuyuki Aihara},

title = {Rigorous Analysis of Quantization Error of an {A/D} Converter Based on {$\beta$}-Map},

booktitle = {Proceedings of 2013 IEEE International Symposium on Circuits and Systems (ISCAS)},

year = 2013,

month = may,

location = {Beijing},

pdf = {iwata-4paper-stamped.pdf}

title = {Preface for Relay Reviews ``Recent Development of Reinforcemeent Learning''},

author = {Takaki Makino and Takeshi Shibuya},

pages = {64-67},

volume = 52,

number = 1,

journal = {Journal of the Society of Instrument and Control Engineers},

year = 2013,

month = jan,

publisher = {Society of Instrument and Control Engineers},

address = {Tokyo},

note = {(In Japanese)}

title = {Exploration-Exploitation Tradeoff and {B}ayesian Environment Models},

author = {Takaki Makino},

pages = {154-161},

volume = 52,

number = 2,

journal = {Journal of the Society of Instrument and Control Engineers},

year = 2013,

month = feb,

publisher = {Society of Instrument and Control Engineers},

address = {Tokyo},

note = {(In Japanese)}

title = {New Optimizer Algorithm for Model Design in Partially Observable Environments},

author = {Takaki Makino and Yasushi Oda and Kazuyuki Aihara},

journal = {Seisan-Kenkyu},

year = 2013,

month = jun,

volume = 65,

number = 3,

pages = {315-318},

note = {(In Japanese)}

title = {Recent trends in Deep Learning and restricted {B}oltzmann machines},

author = {Takaki Makino},

howpublished = {Keynote Speech at FIRST Theme Workshop 19: Deep Learning and Restricted Boltzmann Machines},

year = 2013,

month = mar

author = {Makito Oku and Takaki Makino and Kazuyuki Aihara},

title = {Pseudo-orthogonalization of memory patterns for associative memory},

journal = {IEEE Transactions on Neural Networks and Learning Systems},

pages = {1877-1887},

volume = 24,

number = 11,

year = 2013

author = {Takaki Makino and Yukiko Iwata and Yutaka Jitsumatsu and Masao Hotta and Hao San and Kazuyuki Aihara},

title = {Theoretical Analysis on Quantization Error of {$\beta$}-Encoder},

month = sep,

year = {2013},

booktitle = {IEICE Technical Report},

volume = 113,

number = 224,

pages = {41--44},

note = {Invited Talk (CAS2013-43, NLP2013-55)},

url = {http://www.ieice.org/ken/paper/20130926CBG9/}

title = {Inverse Reinforcement Learning and Imitation Learning in Natural Language Processing},

author = {Yuta Tsuboi and Takaki Makino},

volume = 52,

number = 10,

journal = {Journal of the Society of Instrument and Control Engineers},

year = 2013,

month = oct,

publisher = {Society of Instrument and Control Engineers},

address = {Tokyo},

note = {(In Japanese)},

pages = {922-927}

title = {Panel Discussion: Reinforcement Learning @ 2025 {A.D.} --- Target of Reinforcement Learning Research in the Next Decade},

author = {Takaki Makino and Takeshi Shibuya and Shinichi Shirakawa},

volume = 52,

number = 12,

journal = {Journal of the Society of Instrument and Control Engineers},

year = 2013,

month = dec,

publisher = {Society of Instrument and Control Engineers},

address = {Tokyo},

note = {To appear, (In Japanese)},

pages = {922-927}

author = {Kazuyuki Aihara and Takaki Makino and Makito Oku},

title = {Image Recognition Device, Image Recognition Method, and Program},

year = {2013},

month = {11},

day = {11},

number = {},

type = {Japan Patent},

version = {},

location = {Japan},

yearfiled = {2013},

monthfiled = {11},

dayfiled = {11},

author = {Kazuyuki Aihara and Takaki Makino and Makito Oku},

title = {Image Recognition Device, Image Recognition Method, and Program},

year = {2013},

month = {11},

day = {11},

number = {},

type = {Japan Patent},

version = {},

location = {Japan},

yearfiled = {2013},

monthfiled = {11},

dayfiled = {11},

author = {Makito Oku and Takaki Makino and Kazuyuki Aihara},

title = {A Simple Retrieval Method for Auto-associative Memory Model with {XNOR} Masking},

booktitle = {Proc. of the 3rd International Symposium on Innovative Mathematical Modeling},

month = nov,

pages = 65,

year = 2013

author = {Takaki Makino and Kazuyuki Aihara and Yasushi Oda},

title = {An Efficient Solver for {POMDP} Model Parameters},

booktitle = {Proc. of the 3rd International Symposium on Innovative Mathematical Modeling},

month = nov,

pages = 96,

year = 2013

author = {Taichi Kiwaki and Takaki Makino and Kazuyuki Aihara},

title = {Controlling the Generalization Power of Restricted {B}oltzmann Machines},

booktitle = {Proc. of the 3rd International Symposium on Innovative Mathematical Modeling},

month = nov,

pages = 93,

year = 2013

author = {Katsutoshi Shinohara and Takaki Makino and Yukiko Iwata and Yutaka Jitsumatsu and Masao Hotta and Hao San and Kazuyuki Aihara},

title = {A Simple Estimate of the Quantization Error due to the Uncertainty of $\beta$-valuie for {A/D} Converter based on Beta-Map},

booktitle = {Proc. of the 3rd International Symposium on Innovative Mathematical Modeling},

month = nov,

pages = 118,

year = 2013

author = {Masanori Shiro and Takaki Makino and Kazuyuki Aihara},

title = {Proposal of a New Method in Chemical Simulation},

booktitle = {Proc. of the 3rd International Symposium on Innovative Mathematical Modeling},

month = nov,

pages = 120,

year = 2013

author = {Taichi Kiwaki and Takaki Makino and Kazuyuki Aihara},

title = {Infomation Maximization Training of Restricted {B}oltzmann Machines},

howpublished = {Poster Presentation in Information-Based Induction Science Workshop (IBIS2013) Discussion Track (D-53)},

year = 2013

title = {Approximated Infomax Early Stopping: Revisiting Gaussian {RBM}s on Natural Images},

author = {Kiwaki, Taichi and Makino, Takaki and Aihara, Kazuyuki},

journal = {arXiv preprint arXiv:1312.5412},

year = {2013},

url = {https://arxiv.org/abs/1312.5412}

title = {The {\it q}-exponential probability discounting of gain and loss},

author = {Takahashi, Taiki and Han, Ruokang and Nishinaka, Hiroshi and Makino, Takaki and Fukui, Hiroki},

journal = {Applied Mathematics},

volume = {4},

number = {06},

pages = {876},

year = {2013},

publisher = {Scientific Research Publishing},

url = {https://www.researchgate.net/publication/271296083_The_q_-Exponential_Probability_Discounting_of_Gain_and_Loss}

title = {An efficient model-parameter inverse reinforcement learning software based on parametric description of partially-observable {M}arkov decision process},

author = {Takaki Makino and Masanori Shiro and Kazuyuki Aihara},

booktitle = {Proc. of 28th Annual Conference of Japan Society for Artifical Intelligence},

pages = {2H11},

year = {2014},

organization = {Japan Society for Artificial Intelligence}

title = {{LUKE}---learning underlying knowledge of experts---User Manual},

author = {Makino, Takaki and Shiro, Masanori},

howpublished = {Distributed with OSS software LUKE},

year = {2014}

title = {Reinforcement learning studies being practicalized},

author = {Takaki Makino},

journal = {Seisan-kenkyu},

volume = {66},

number = {3},

pages = {305--308},

year = {2014},

publisher = {Institute of Industrial Science, the University of Tokyo},

note = {(In Japanese)}

title = {Neuroeconomics of psychopathy: risk taking in probability discounting of gain and loss predicts psychopathy},

author = {Takahashi, Taiki and Takagishi, Haruto and Nishinaka, Hirofumi and Makino, Takaki and Fukui, Hiroki},

journal = {Neuroendocrinology Letters},

volume = {35},

number = {6},

pages = {510--517},

year = {2014},

url = {https://www.researchgate.net/publication/269115275_Neuroeconomics_of_psychopathy_Risk_taking_in_probability_discounting_of_gain_and_loss_predicts_psychopathy}

title = {Finding more mobile-friendly search results},

author = {Makino, Takaki and Jung, Chaesang and Phan, Doantam},

journal = {Official Google Webmaster Central Blog},

volume = {21},

url = {https://webmasters.googleblog.com/2015/02/finding-more-mobile-friendlysearch.html},

year = {2015}

title = {Rolling out the mobile-friendly update},

author = {Makino, Takaki and Phan, Doantam},

journal = {Official Google Webmaster Central Blog},

volume = {21},

url = {https://webmasters.googleblog.com/2015/04/rolling-out-mobile-friendly-update.html},

year = {2015}

title = {Rigorous estimates of quantization error for {A/D} converters based on beta-map},

author = {Makino, Takaki and Iwata, Yukiko and Shinohara, Katsutoshi and Jitsumatsu, Yutaka and Hotta, Masao and San, Hao and Aihara, Kazuyuki},

journal = {Nonlinear Theory and Its Applications, IEICE},

volume = {6},

number = {1},

pages = {99--111},

year = {2015},

publisher = {The Institute of Electronics, Information and Communication Engineers},

url = {https://www.jstage.jst.go.jp/article/nolta/6/1/6_99/_article}

title = {Advanced Reinforcement Learning},

author = {Takaki Makino and Takeshi Shibuya and Shinichi Shirakawa and Minoru Asada and Hideki Asoh and Sachiyo Arai and Hitoshi Iima and Makoto Itoh and Kazuhiro Ohkura and Yasuaki Kuroe and Norikazu Sugimoto and Yuuta Tsuboi and Kenji Doya and Tohgoroh Matsui and Shin-ichi Maeda and Kazumitsu Miyazaki and Yasuhiro Minami and Toyomi Meguro and Tetsuro Morimura and Jun Morimoto and Toshiyuki Yasuda and Junichiro Yoshimoto},

year = {2016},

isbn = {4627880316},

publisher = {Morikita Publishing},

address = {Chiyoda-ku, Tokyo},

note = {(In Japanese)}

title = {This is how artifical intelligence is created},

author = {Aihara, Kazuyuki and Makino, Takaki and Kanayama, Hiroshi and Kohno, Takashi and Kiwaki, Taichi and Aono, Masashi},

year = 2017,

isbn = {4863101856},

publisher = {Wedge Inc.},

address = {Chiyoda-ku, Tokyo},

note = {(In Japanese)}

title = {Apprenticeship learning and inverse reinforcement learning},

author = {Takaki Makino},

booktitle = {Encyclopedia of Artificial Intelligence},

publisher = {Kyoritsu Publishing},

year = 2017,

pages = {305--307},

isbn = {978-4-320-12420-2},

note = {(In Japanese)}

title = {Tutorial Talk: Applying Reinforcement Learning to Practical Problems},

month = jun,

year = 2018,

booktitle = {IEICE Technical Report},

volume = 118,

number = 126,

pages = {129},

note = {(SR2018-48)},

url = {https://www.ieice.org/ken/paper/20180712w14U/}

title = {Recurrent Neural Network Transducer for Audio-Visual Speech Recognition},

author = {Makino, Takaki and Liao, Hank and Assael, Yannis and Shillingford, Brendan and Garcia, Basilio and Braga, Otavio and Siohan, Olivier},

booktitle = {IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2019)},

url = {https://arxiv.org/abs/1911.04890},

year = {2019}