259 Hits in 8.7 sec

Better Living Through Chemistry: Evolving GasNets for Robot Control

Phil Husbands, Tom Smith, Nick Jakobi, Michael O'Shea
1998 Connection science  
A series of evolutionary runs with and without the gas modulation active demonstrated that networks incorporating modulation by diffusing gases evolved to produce successful controllers considerably faster  ...  This paper introduces a new type of artificial neural network (GasNets) and shows that it is possible to use evolutionary computing techniques to find robot controllers based on them.  ...  Many thanks to Pedro Paulo Balbi de Oliveira, Andy Philippides, John Anderson, Emmet Spier, Tom Ziemke, Carmen Ruybal, three anonymous reviewers and various members of the CCNR, COGS and BIOLS for useful  ... 
doi:10.1080/095400998116404 fatcat:zkwg3tup3zdepg3bqp3n6pip6m

Conceptual Representations for Computational Concept Creation

Ping Xiao, Alexandre Miguel Pinto, Alberto Díaz, Virginia Francisco, Pablo Gervás, Raquel Hervás, Carlos León, Jamie Forth, Matthew Purver, Geraint A. Wiggins, Dragana Miljković, Hannu Toivonen (+16 others)
2019 ACM Computing Surveys  
The creation of new concepts is a central challenge for any creative system.  ...  Additionally, conceptual representations used in particular creative domains, such as language, music, image and emotion, are reviewed separately.  ...  There exist collections of evaluation ratings estimated by computational methods, called affect lexicons, such as General Inquirer, 3 WordNet-AFFECT (Strapparava and Valitutti 2004) , SentiWord-Net (  ... 
doi:10.1145/3186729 fatcat:yhsrmlj2w5af3iy7opexxh22hm

Logical Versus Analogical or Symbolic Versus Connectionist or Neat Versus Scruffy

Marvin Minsky
1991 The AI Magazine  
Acknowledgment This research was funded over a period of years by the Computer Science Division of the Office of Naval Research. Illustrations by Juliana Minsky.  ...  What do we mean by connectionist?  ...  However, of what use would such a model be if it merely repeated redundantly?  ... 
doi:10.1609/aimag.v12i2.894 dblp:journals/aim/Minsky91 fatcat:n2p4vsqesnanlm5f33adaphwai

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.  ...  The level of analysis is intermediate between those of symbolic cognitive models and neural models.  ...  way, and is associated in some way to a fine-grained subsymbolic, parallel, etc. process modeled by connectionist nets.  ... 
doi:10.1017/s0140525x00052791 fatcat:7o7kyja25jfztfovklj74nqt3y

A Survey of Artificial Cognitive Systems: Implications for the Autonomous Development of Mental Capabilities in Computational Agents

David Vernon, Giorgio Metta, Giulio Sandini
2007 IEEE Transactions on Evolutionary Computation  
We present a broad survey of the various paradigms of cognition, addressing cognitivist (physical symbol systems) approaches, emergent systems approaches, encompassing connectionist, dynamical, and enactive  ...  robotic platforms with the aim of implementing bioinspired models of sensorimotor control.  ...  ACKNOWLEDGMENT The authors would like to acknowledge the many helpful comments of the two anonymous referees on earlier versions of this paper.  ... 
doi:10.1109/tevc.2006.890274 fatcat:s3ueaficnjbebkrfnend4ahpau

Dynamical systems and cognitive linguistics: toward an active morphodynamical semantics

René Doursat, Jean Petitot
2005 Neural Networks  
Our objective is to categorize the infinite diversity of schematic visual scenes into a small set of grammatical elements and elucidate the topology of language.  ...  We suggest that this invariance can be explained by introducing morphodynamical transforms, which erase image details and create virtual structures or singularities (boundaries, skeleton), and call this  ...  Acknowledgements R.D. is grateful to Philip Goodman for welcoming him in his UNR lab, and to J.P. for his warm encouragements.  ... 
doi:10.1016/j.neunet.2005.06.009 pmid:16085386 fatcat:tpaofjiwlzbfraeyftnba2i2dq

Synthetic Neuroethology

Pete Mandik
2002 Metaphilosophy  
Computation is considered as an object, as a method, and as a model used in a certain line of philosophical inquiry concerning the relation of mind to matter.  ...  As method and model, the computational techniques of artificial life and embodied evolutionary connectionism are used to conduct prosthetically enhanced thought experiments concerning the evolveability  ...  Acknowledgements This work was supported in part by a grant from the McDonnell Project in Philosophy and the Neurosciences.  ... 
doi:10.1111/1467-9973.00214 fatcat:qufctd532feb5drmhmhqxfji5q

Coordination and control structures and processes: possibilities for connectionist networks (CN)

1990 Journal of experimental and theoretical artificial intelligence (Print)  
Whatever control mechanisms might be necessary are largely expected to emerge as a function of interactions among very simple individual units, and of learning.  ...  of use in CN.  ...  processes/transforms applied to particular segments of the image.  ... 
doi:10.1080/09528139008953727 fatcat:ddo73sudqvabzhaknne4uhxsja

Modularity, criticality, and evolvability of a developmental gene regulatory network

Berta Verd, Nicholas AM Monk, Johannes Jaeger
2019 eLife  
Some subcircuits are in a state of criticality, while others are not, which explains the observed differential evolvability of the various expression features in the system.  ...  Traditionally, functional modularity is approximated by detection of modularity in network structure. However, the correlation between structure and function is loose.  ...  Acknowledgements We would like to thank Anton Crombach for insightful discussions, comments on the manuscript, and for providing the fitted full model used in this analysis.  ... 
doi:10.7554/elife.42832 pmid:31169494 pmcid:PMC6645726 fatcat:wamkjuezgzhy3bjk5pv3m2pute

A Connectionist Approach to Spatial Memory and Planning [chapter]

G. Bugmann
1998 Perspectives in Neural Computing  
The sparse neural network model described here is characterized by: i) the use of a resistive-grid paradigm for backward planning, transforming the view-graph into a dynamic value-map ii) the use of a  ...  Two forms of connectionist implementation of these principles are discussed, using a sparse or a distributed representation of states.  ...  I gratefully acknowledge comments by M i k e Denham, Philippe Gaussier and Loukas Michalis on earlier versions of the manuscript.  ... 
doi:10.1007/978-1-4471-3427-5_5 fatcat:gc42ys6wa5bajnekd4oqgma3gu

Connectionist modelling in psychology: A localist manifesto

Mike Page
2000 Behavioral and Brain Sciences  
It can be applied to a number of problems that are difficult for fully distributed models, and its applicability can be extended through comparisons with a number of classic mathematical models of behaviour  ...  Localist models are characterized by the presence of localist representations rather than the absence of distributed representations.  ...  ACKNOWLEDGMENT This work was supported in part by NSF grants SBR-9720398 and ECS-9970890.  ... 
doi:10.1017/s0140525x00003356 fatcat:6hnhqgbdtvcbtggl75dafiwlsi

How brains make chaos in order to make sense of the world

Christine A. Skarda, Walter J. Freeman
1987 Behavioral and Brain Sciences  
Recent "connectionist" models provide a new explanatory alternative to the digital computer as a model for brain function.  ...  The results indicate the existence of sensory-and motor-specific information in the spatial dimension of EEG activity and call for new physiological metaphors and techniques of analysis.  ...  In our neural model, as in connectionist models, there is no discrete semantic interpretation given to activity in a neural net or to elements of the net; this activity varies not only with the presence  ... 
doi:10.1017/s0140525x00047336 fatcat:5gc3xtfbyfexfinu7enjclchza

Localist representation can improve efficiency for detection and counting

Horace Barlow, Anthony Gardner-Medwin
2000 Behavioral and Brain Sciences  
It can be applied to a number of problems that are difficult for fully distributed models, and its applicability can be extended through comparisons with a number of classic mathematical models of behaviour  ...  Localist models are characterized by the presence of localist representations rather than the absence of distributed representations.  ...  ACKNOWLEDGMENT This work was supported in part by NSF grants SBR-9720398 and ECS-9970890.  ... 
doi:10.1017/s0140525x00223352 fatcat:zeo65fd76vh4nblxjvlahq3vgm

The Newell Test for a theory of cognition

John R. Anderson, Christian Lebiere
2003 Behavioral and Brain Sciences  
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.  ...  The complete list of published ACT-R models between 1997 and 2002 is available from the ACT-R home page at 2 cognitive development.  ...  ACKNOWLEDGMENTS Preparation of this manuscript was supported by ONR grant N00014-96-1-C491. We would like to thank Gary Marcus and Alex Petrov for their comments on this manuscript.  ... 
doi:10.1017/s0140525x0300013x fatcat:e7frlerkdjgthnsv5vy6nq7tbq

Stability and Intermittency in Large-Scale Coupled Oscillator Models for Perceptual Segmentation

Cees van Leeuwen, Mark Steyvers, Maarten Nooter
1997 Journal of Mathematical Psychology  
The coupled map lattice, a system of locally coupled nonlinear maps, is proposed as a model for perceptual segmentation.  ...  Patterns of synchronized activity are obtained in the model from high-dimensional, deterministic chaos. These patterns correspond to segmented topographical mappings of the visual field.  ...  For the present model we have chosen a provisional solution which models selective facilitation by means of an algorithm.  ... 
doi:10.1006/jmps.1997.1177 pmid:9473396 fatcat:a2xx7ng3lfhglfe5zt7lhaq6ye
« Previous Showing results 1 — 15 out of 259 results