Filters








1,561 Hits in 11.7 sec

A Connectionist-Symbolic Approach to Modeling Agent Behavior: Neural Networks Grouped by Contexts [chapter]

Amy E. Henninger, Avelino J. Gonzalez, Michael Georgiopoulos, Ronald F. DeMara
2001 Lecture Notes in Computer Science  
This paper supports this solicitation by examining the use of a context structure to modularly organize the application of neural networks to a low-level Semi-Automated Forces (SAF) reactive task.  ...  A recent report by the National Research Council (NRC) declares neural networks "hold the most promise for providing powerful learning models".  ...  Specifically, this research examines the performance improvements made to a neural network based near-term movement model by adopting a modular approach that groups neural networks according to contexts  ... 
doi:10.1007/3-540-44607-9_15 fatcat:iwjsrgbaffh6nhipjbbbnkpuc4

Editorial Commentary

1988 Behavioral and Brain Sciences  
A set of hypotheses is formulated for a connectionist approach to cognitive modeling. These hypotheses are shown to be incompatible with the hypotheses underlying traditional cognitive models.  ...  Higher-level analyses of these connectionist models reveal subtle relations to symbolic models.  ...  There is a difference between thinking that someone loves everyone and that everyone is loved by someone or other; symbolic approaches capture this kind of difference by relating the agent to systematically  ... 
doi:10.1017/s0140525x00052791 fatcat:7o7kyja25jfztfovklj74nqt3y

Behavioral personal digital assistants: The seventh generation of computing

Kenneth R. Stephens, William R. Hutchison
1992 The Analysis of Verbal Behavior  
The latter approach is consistent with developments in the field of "neural networks."  ...  The alternative is a system that models the behavioral repertoire as a network of associations between antecedent stimuli and operants, and adapts when supplied with reinforcement.  ...  a symbolic, logical approach.  ... 
doi:10.1007/bf03392881 pmid:22477053 pmcid:PMC2748594 fatcat:jfgiofds5zb3ldlbgh7kvdsfpa

Adaptive Behavior in Autonomous Agents

Tom Ziemke
1998 Presence - Teleoperators and Virtual Environments  
The behavior-oriented approach, with its focus on the interaction between autonomous agents and their environments, is introduced by contrasting it with the traditional approach of knowledge-based AI.  ...  It is concluded that in order to realize truly autonomous and intelligent agents, the behavior-oriented approach will have to focus even more on life-like qualities in both agents and environments.  ...  50 Hence, possibly as an intermediate step, virtual environments would be extremely useful tools for behavior-oriented AI experimentation if they could provide sufficiently lifelike agents, environments  ... 
doi:10.1162/105474698565947 fatcat:6ck7uwun4vgw5mxf33v2l6ryua

Relational priming: Obligational nitpicking

Varol Akman
2008 Behavioral and Brain Sciences  
To illustrate this, we present a computational (here connectionist) account where analogy arises gradually as a by-product of pattern completion in a recurrent network.  ...  The network exhibits behaviors consistent with a broad range of key phenomena from the developmental literature, lending support to the appropriateness of this approach (using low-level cognitive mechanisms  ...  There are of course other requirements for a cognitive scientific explanation. Neural plausibility, for example, is one. This is addressed with respect to ARP in section R7.3.  ... 
doi:10.1017/s0140525x08004470 fatcat:eh4mtn3dsfcmlepw6xtz36vpay

Developing structured representations

Leonidas A. A. Doumas, Lindsey E. Richland
2008 Behavioral and Brain Sciences  
To illustrate this, we present a computational (here connectionist) account where analogy arises gradually as a by-product of pattern completion in a recurrent network.  ...  The network exhibits behaviors consistent with a broad range of key phenomena from the developmental literature, lending support to the appropriateness of this approach (using low-level cognitive mechanisms  ...  There are of course other requirements for a cognitive scientific explanation. Neural plausibility, for example, is one. This is addressed with respect to ARP in section R7.3.  ... 
doi:10.1017/s0140525x08004536 fatcat:5tirqvquffduhpjsviocnbuavq

Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes

Yuuya Sugita, Jun Tani
2005 Adaptive Behavior  
We present a novel connectionist model for acquiring the semantics of a simple language through the behavioral experiences of a real robot.  ...  Our experimental results showed that the essential structures for situated semantics can self-organize themselves through dense interactions between linguistic and behavioral processes whereby a certain  ...  Our model is composed of two loosely coupled connectionist networks referred to as the recurrent neural network with parametric bias nodes (RNNPB) (Tani, 2003; Tani & Ito, 2003; Ito & Tani, 2004a) , one  ... 
doi:10.1177/105971230501300102 fatcat:6y3qnp34jbahvhfmocvxacj5ny

Analogical inferences are central to analogy

Arthur B. Markman, Jeffrey P. Laux
2008 Behavioral and Brain Sciences  
To illustrate this, we present a computational (here connectionist) account where analogy arises gradually as a by-product of pattern completion in a recurrent network.  ...  The network exhibits behaviors consistent with a broad range of key phenomena from the developmental literature, lending support to the appropriateness of this approach (using low-level cognitive mechanisms  ...  There are of course other requirements for a cognitive scientific explanation. Neural plausibility, for example, is one. This is addressed with respect to ARP in section R7.3.  ... 
doi:10.1017/s0140525x08004603 fatcat:owr2dlbwevbglncjkb2pbdbucq

Nonclassical connectionism should enter the decathlon

Francisco Calvo Garzón
2003 Behavioral and Brain Sciences  
Its weaknesses derive from its failure to acknowledge a symbolic level to thought. In contrast, ACT-R includes both symbolic and subsymbolic components.  ...  There would be greater theoretical progress if we evaluated theories by a broad set of criteria such as these and attended to the weaknesses such evaluations revealed.  ...  ACKNOWLEDGMENTS ACKNOWLEDGMENT This work was supported in part by ARI contract DASW01-00 -K-0012.  ... 
doi:10.1017/s0140525x03240139 fatcat:qzqkqm6ejvelzostaoc4lfp6ni

Analogy as relational priming: The challenge of self-reflection

Andrea Cheshire, Linden J. Ball, Charlie N. Lewis
2008 Behavioral and Brain Sciences  
To illustrate this, we present a computational (here connectionist) account where analogy arises gradually as a by-product of pattern completion in a recurrent network.  ...  The network exhibits behaviors consistent with a broad range of key phenomena from the developmental literature, lending support to the appropriateness of this approach (using low-level cognitive mechanisms  ...  There are of course other requirements for a cognitive scientific explanation. Neural plausibility, for example, is one. This is addressed with respect to ARP in section R7.3.  ... 
doi:10.1017/s0140525x08004500 fatcat:eq6gsq74rzhlhkywam53pzg63y

A connectionist theory of phenomenal experience

Gerard O'Brien, Jonathan Opie
1999 Behavioral and Brain Sciences  
, and on the other, by the classical computational theory of mind -the theory that takes human cognition to be a species of symbol manipulation.  ...  Connectionists, on the other hand, are in a position to explore a vehicle theory of phenomenal experience. In this paper we develop and defend this vehicle theory.  ...  , Ian Ravenscroft, John Sutton and a number of anonymous referees of this journal for their very helpful comments on earlier versions of this paper.  ... 
doi:10.1017/s0140525x9900179x fatcat:suekvsjsfnb2faoymtugicpteq

The Newell Test for a theory of cognition

John R Anderson, Christian Lebiere
2003 Behavioral and Brain Sciences  
Its weaknesses derive from its failure to acknowledge a symbolic level to thought. In contrast, ACT-R includes both symbolic and sub-symbolic components.  ...  There would be greater theoretical progress if we evaluated theories by a broad set of criteria such as these and attended to the weaknesses such evaluations revealed.  ...  ACKNOWLEDGMENTS ACKNOWLEDGMENT This work was supported in part by ARI contract DASW01-00 -K-0012.  ... 
pmid:15179936 fatcat:ee3ukbaef5dvneqydsyyxz4lre

Relation priming, the lexical boost, and alignment in dialogue

Claudine N. Raffray, Martin J. Pickering, Holly P. Branigan
2008 Behavioral and Brain Sciences  
s model is based on a neural network implementing a Hebbian learning algorithm which is able to enhance bit by bit the strategy for analogy-making and explicitly model the development from superficial  ...  More precisely, the network can learn causal relations using a transformation of an object (e.g., "apple") by a causal agent (e.g., "knife") to achieve a representation of a transformed object (e.g., "  ... 
doi:10.1017/s0140525x08004640 fatcat:xtjff5i3k5eqzp4lsr4zxmag6q

APPROACHES TO GROUNDING SYMBOLS IN PERCEPTUAL AND SENSORIMOTOR CATEGORIES [chapter]

ANGELO CANGELOSI
2005 Handbook of Categorization in Cognitive Science  
Two main modeling approaches to the symbol grounding are presented: (i) the connectionist approach, based on artificial neural networks for category learning and naming tasks, and (ii) the embodied modeling  ...  approach, based on adaptive agent simulations and cognitive robots.  ...  Linking Vision and Language: Connectionist Approaches to Category Learning and Symbol Grounding Connectionist Modeling of Category Learning and Naming The great majority of neural network models of symbol  ... 
doi:10.1016/b978-008044612-7/50087-1 fatcat:eo26232zzvd3dlwdkbmlcbvlma

Analogy as relational priming: A developmental and computational perspective on the origins of a complex cognitive skill

Robert Leech, Denis Mareschal, Richard P. Cooper
2008 Behavioral and Brain Sciences  
To illustrate this, we present a computational (here connectionist) account where analogy arises gradually as a by-product of pattern completion in a recurrent network.  ...  The network exhibits behaviors consistent with a broad range of key phenomena from the developmental literature, lending support to the appropriateness of this approach (using low-level cognitive mechanisms  ...  There are of course other requirements for a cognitive scientific explanation. Neural plausibility, for example, is one. This is addressed with respect to ARP in section R7.3.  ... 
doi:10.1017/s0140525x08004469 pmid:18662435 fatcat:c5fzdlzb4bdtxkofcj7mtckbfi
« Previous Showing results 1 — 15 out of 1,561 results