Straightforward reinforcement learning for multi-agent co-learning settings often results in poor outcomes. Meta-learning processes beyond straightforward reinforcement learning may be necessary to achieve good (or optimal) outcomes. Algorithmic processes of meta-learning, or "manipulation", will be described, which is a cognitively realistic and effective means for learning cooperation. We will discuss various "manipulation" routines that address the issue of improving multi-agent co-learning. We hope to develop better adaptive means of multi-agent cooperation, without requiring a priori knowledge, and advance multi-agent co-learning beyond (...) existing theories and techniques. (shrink)

This paper explores the interaction between implicit and explicit processes during skill learning, in terms of top-down learning (that is, learning that goes from explicit to implicit knowledge) versus bottom-up learning (that is, learning that goes from implicit to explicit knowledge). Instead of studying each type of knowledge (implicit or explicit) in isolation, we stress the interaction between the two types, especially in terms of one type giving rise to the other, and its effects on learning. The work presents an (...) integrated model of skill learning that takes into account both implicit and explicit processes and both top-down and bottom-up learning. We examine and simulate human data in the Tower of Hanoi task. The paper shows how the quantitative data in this task may be captured using either top-down or bottom-up approaches, although top-down learning is a more apt explanation of the human data currently available. These results illustrate the two different directions of learning (top-down versus bottom-up), and thereby provide a new perspective on skill learning. Ó 2003 Elsevier B.V. All rights reserved. (shrink)

This article explores the view that computational models of cognition may constitute valid theories of cognition, often in the full sense of the term ‘‘theory”. In this discussion, this article examines various (existent or possible) positions on this issue and argues in favor of the view above. It also connects this issue with a number of other relevant issues, such as the general relationship between theory and data, the validation of models, and the practical benefits of computational modeling. All the (...) discussions point to the position that computational cognitive models can be true theories of cognition. Ó 2008 Elsevier B.V. All rights reserved. (shrink)

This Neurocomputing special issue is based on selected, expanded and significantly revised versions of papers presented at the Second International Conference on Brain Inspired Cognitive Systems (BICS 2006) held at Lesvos, Greece, from 10 to 14 October 2006. The aim of BICS 2006, which followed the very successful first BICS 2004 held at Stirling, Scotland, was to bring together leading scientists and engineers who use analytic, syntactic and computational methods both to understand the prodigious processing properties of biological systems and, (...) specifically, of the brain, and to exploit such knowledge to advance computational methods towards ever higher levels of cognitive competence. The biennial BICS Conference Series (with BICS 2008 recently held in Sao Luis, Brazil, 24–27 June, and BICS 2010 due to be held in Madrid, Spain) aims to become a major point of contact for research scientists, engineers and practitioners throughout the world in the fields of cognitive and computational systems inspired by the brain and biology. The first paper in this special issue is by Carnell who presents an analysis of the use of Hebbian and Anti-Hebbian spike timedependent plasticity (STDP) learning functions within the context of recurrent spiking neural networks. He shows that under specific conditions Hebbian and Anti-Hebbian learning can be considered approximately equivalent. Finally, the author demonstrates that such a network habituates to a given stimulus and is capable of detecting subtle variations in the structure of the stimuli itself. Hodge, O’Keefe and Austin present a binary neural shape matcher using Johnson counters and chain codes. They show that images may be matched as whole images or using shape matching. Finally, they demonstrate shape matching using a binary associative-memory neural network to index and match chain codes where the chain code elements are represented by Johnson codes. (shrink)

This paper addresses weighting and partitioning in complex reinforcement learning tasks, with the aim of facilitating learning. The paper presents some ideas regarding weighting of multiple agents and extends them into partitioning an input/state space into multiple regions with di erential weighting in these regions, to exploit di erential characteristics of regions and di erential characteristics of agents to reduce the learning complexity of agents (and their function approximators) and thus to facilitate the learning overall. It analyzes, in reinforcement learning (...) tasks, di erent ways of partitioning a task and using agents selectively based on partitioning. Based on the analysis, some heuristic methods are described and experimentally tested. We nd that some o -line heuristic methods performed the best, signi cantly better than single-agent models. (shrink)

Theories of reference have been central to analytic philosophy, and two views, the descriptivist view of reference and the causal-historical view of reference, have dominated the field. In this research tradition, theories of reference are assessed by consulting one's intuitions about the reference of terms in hypothetical situations. However, recent work in cultural psychology has shown systematic differences between East Asians and Westerners, and some work indicates that this extends to intuitions about philosophical cases. In light of these findings on (...) cultural differences, two experiments were conducted which explored intuitions about reference in Westerners and East Asians. Both experiments indicate that, for certain central cases, Westerners are more likely than East Asians to report intuitions that are consistent with the causal-historical view. These results constitute prima facie evidence that semantic intuitions vary from culture to culture, and that paper argues that this fact raises questions about the nature of the philosophical enterprise of developing a theory of reference. (shrink)

日本哲学の最前線。西田幾多郎に始まる日本哲学を、現代哲学のコンテクストのもとで六つのテーゼに集約し、新たな第七の「悲のテーゼ」を導き出す。.

In the physical sciences a rigorous theory is a hierarchy of descriptions in which causal relationships between many general types of entity at a phenomenological level can be derived from causal relationships between smaller numbers of simpler entities at more detailed levels. The hierarchy of descriptions resembles the modular hierarchy created in electronic systems in order to be able to modify a complex functionality without excessive side effects. Such a hierarchy would make it possible to establish a rigorous scientific theory (...) of consciousness. The causal relationships implicit in definitions of access consciousness and phe- nomenal consciousness are made explicit, and the corresponding causal relationships at the more detailed levels of perception, memory, and skill learning described. Extension of these causal relationships to physiological and neural levels is discussed. The general capability of a range of current consciousness models to support a modular hierarchy which could generate these causal relationships is reviewed, and the specific capabilities of two models with good general capabilities are compared in some detail. Ó 2003 Elsevier Inc. All rights reserved. (shrink)

This paper introduces a hybrid model that combines connectionist, symbolic, and reinforcement learning for tackling reactive sequential decision tasks by a situated agent. Both procedural skills and high-level symbolic representations are acquired through an agent's experience interacting with the world, in a bottom-up direction. It deals with on-line learning, that is, learning continuously from on-going experience in the world, without the use of preconstructed data sets or preconceived concepts. The model is a connectionist one based on a two-level approach proposed (...) earlier. Acknowledgements: This work is supported in part by O ce of Naval Research grant N00014-95-1-0440. (shrink)

無我や輪廻とも関わる、行動とその潜在的な影響力を意味する業の思想について、パーリ聖典を中心に明らかにする画期的な論考。.

In lieu of an abstract, here is a brief excerpt of the content:Reviewed by:Latina/o Social Ethics: Moving beyond Eurocentric Moral Thinking, and: Racism and God-Talk: A Latino/a PerspectiveKevin N. York-SimmonsLatina/o Social Ethics: Moving beyond Eurocentric Moral Thinking Miguel A. de La Torre, Waco Tex.: Baylor University Press, 2010. 160 pp. $24.95.Racism and God-Talk: A Latino/a Perspective Rubén Rosario Rodríguez New York: New York University Press, 2008. 320 pp. $24.00Although Latina/o theologians have contributed much to Christian moral discourse in recent decades, (...) the impact of these contributions has too often remained limited to other Latina/os and those with particular interests in liberation theologies. Miguel de La Torre and Rubén Rosario Rodríguez build on the contributions of theologians before them while challenging the broader theological community to take notice of these rich and provocative works.In four concise chapters, Miguel de La Torre’s Latina/o Social Ethics delivers a forceful criticism of prominent thinkers in the field of Christian ethics and offers a creative reconstruction of ethics from a Latina/o perspective. De La Torre offers a critique of “Euroamerican” Christian ethicists whose works have greatly influenced contemporary Christian moral discourse. He addresses the writings of Walter Rauschenbusch, Reinhold Niebuhr, Stanley Hauerwas, Anthony Campolo, Ron Sider, and Jim Wallis. De La Torre faults these theologians for the ways in which their moral thinking participates in the oppression and marginalization of Latina/os, either through their silence or through their endorsement of specific polices. De La Torre concludes that the legacy of cultural and economic privilege and the oppression of Latinas/os are so [End Page 199] deeply embedded in the Eurocentric thinking that has dominated the field of Christian ethics that it cannot be the foundation for Latino social ethics.De La Torre’s aim is to “move beyond” Eurocentric modes of thinking rather than dwell on critique. This eagerness to move forward to the creative and constructive aspects of Latina/o ethics, however, limits the forcefulness of his critique of Euroamerican ethicists. De La Torre’s reading of Euroamerican ethics—and even the application of that term—is highly selective, both in terms of the thinkers chosen and the writings examined. While De La Torre’s criticisms of these thinkers are generally insightful and serve to illustrate his basic criticism of Eurocentric ethics, these criticisms are limited in their depth of analysis. De La Torre is less concerned with the broader historical and theological considerations at work in these Euroamerican ethicists than with their failures to adequately address issues of concern to Latinas/os.The second half of Latina/o Social Ethics moves to his constructive, or “reconstructive,” project. De La Torre reviews central concepts in the methodology of Latina/o social ethics, including lo cotidiano, nepantla, la lucha, en conjunto, and acompañamiento. De La Torre’s explanation of these terms is brief and accessible. Moving beyond these concepts, the fourth chapter of Latina/o Social Ethics offers a creative approach to a liberative ethics that draws on Christian tradition as well as broader Hispanic cultural resources, including folk characters and themes of the trickster found in Afro-Caribbean religious traditions. De La Torre addresses the concern for how to imagine a Christian ethics with a role for the trickster, including identifying trickster characters and themes in the Bible. His “disruptive ethics” challenges the preference for order over justice that has characterized Eurocentric ethics, for which he provides helpful examples. De La Torre is clearly concerned with imperialism, immigration, and free trade, yet it is unclear what justice means in those contexts. Perhaps due to the powerlessness of marginalized Latina/os, criticisms of injustice weigh far more heavily than visions of justice.The concise length of this book broadens its appeal. Academics unfamiliar with some of the concepts and methodologies of Latina/o theologians will find this short introduction a useful starting point. This provocative book would also be a welcome addition to the classroom, either in part or in its entirety.In contrast to De La Torre’s short work, Rubén Rosario Rodríguez sets a broader and more ambitious task in his Racism and God-Talk. His project... (shrink)

1. Sŏron -- 2. Hyŏnmo yangch'ŏ sasang ŭi yuip kwa yŏsŏnggwan ŭi pyŏnhwa -- 3. Kŭndaegi kajok chedo wa hyŏnmo yangch'ŏ tamnon -- 4. Kungmin ŭl yangsŏng hanŭn hyŏnmo ŭi chaehyŏn -- 5. Sin'gajŏng ŭi anchuin yangch'ŏ ŭi chaehyŏn -- 7. Kyŏllon.

Competition among scientists for funding, positions and prestige, among other things, is often seen as a salutary driving force in U.S. science. Its effects on scientists, their work and their relationships are seldom considered. Focus-group discussions with 51 mid- and early-career scientists, on which this study is based, reveal a dark side of competition in science. According to these scientists, competition contributes to strategic game-playing in science, a decline in free and open sharing of information and methods, sabotage of others’ (...) ability to use one’s work, interference with peer-review processes, deformation of relationships, and careless or questionable research conduct. When competition is pervasive, such effects may jeopardize the progress, efficiency and integrity of science. (shrink)

1. Sŏron -- 2. Ŭisik ŭi chonggyojŏk ch'ŭngmyŏn -- 3. Yŏng : Chŏng Yag-yong ŭi simnon -- 4. Yŏngch'e : Chŏng Yag-yong ŭi insŏngnon -- 5. 'Yŏngch'e' insŏngnon esŏ pon ch'ŏnin kwan'gye -- 6. Kyŏllon.

1. Sŏron -- 2. Kŭndae wa chonggyo, kŭrigo sinjonggyo -- 3. Han'guk kŭndae sinjonggyo ŭi t'ansaeng -- 4. Han'guk kŭndae sinjonggyo ŭi kyŏngjŏn kwa ŭirye -- 5. Kaebyŏk sasang kwa chisang ch'ŏn'guk -- 6. Kaebyŏk sasang ŭi chonggyobyŏl chŏn'gae -- 7. Kaebyŏk chonggyodŭl ŭi sahoesachŏk chŏn'gae -- 8. Kyŏllon kwa kŭndae ihu.

The Repugnant Conclusion served an important purpose in catalyzing and inspiring the pioneering stage of population ethics research. We believe, however, that the Repugnant Conclusion now receives too much focus. Avoiding the Repugnant Conclusion should no longer be the central goal driving population ethics research, despite its importance to the fundamental accomplishments of the existing literature.

"Why should we care about having true beliefs? And why do demonstrably false beliefs persist and spread despite consequences for the people who hold them? Philosophers of science Cailin O’Connor and James Weatherall argue that social factors, rather than individual psychology, are what’s essential to understanding the spread and persistence of false belief. It might seem that there’s an obvious reason that true beliefs matter: false beliefs will hurt you. But if that’s right, then why is it irrelevant to many (...) people whether they believe true things or not? In an age riven by "fake news," "alternative facts," and disputes over the validity of everything from climate change to the size of inauguration crowds, the authors argue that social factors, not individual psychology, are what’s essential to understanding the persistence of false belief and that we must know how those social forces work in order to fight misinformation effectively."–Publisher’s description. (shrink)

It has been widely accepted that intentional actions are “the actions to which “a certain sense of the question ‘why?’ is given application” (Anscombe 1957/2000: 9). But there are robust reasons for thinking that this claim is false. First, there are intentional actions for which such questions are unsound. We have good reasons for thinking that the questions are not “given application” in these cases. Second, when these questions are “given application” this is best explained, it is argued, not in (...) terms of a necessary link between intentional action and this type of enquiry, but in terms of the fact that this is an enquiry that we pursue when we take an agent to have exercised certain of their rational capacities. (shrink)

Brian O'Shaughnessy puts forward a bold and original theory of consciousness, one of the most fascinating but puzzling aspects of human existence. He analyses consciousness into purely psychological constituents, according pre-eminence to its epistemological power; the result is an integrated picture of the conscious mind in its natural physical setting. Consciousness and the World is a rich and exciting book, a major contribution to our understanding of the mind.