Abstract

This paper describes and motivates six principles for computational cognitive neuroscience models: biological realism, distributed representations, inhibitory competition, bidirectional activation propagation, errordriven task learning, and Hebbian model learning. Although these principles are supported by a number of cognitive, computational, and biological motivations, the prototypical neural network model (a feedforward backpropagation network) incorporates only two of them, and no widely used model incorporates all of them. This paper argues that these principles should be integrated into a coherent overall framework, and discusses some potential synergies and conflicts in doing so.

Citations

2307	Learning internal representations by error propagation - Rumelhart, Hinton, et al. - 1986
1158	Self-organization and associative memory - Kohonen - 1984
764	S.: A solution to plato’s problem: The latent semantic analysis theory of acquisition, induction and representation of knowledge. Psychological Review 104 - Landauer, Dumais - 1997
721	The organization of behavior - Hebb - 1949
684	DJ: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature - BA, Field - 1996
665	Adaptive mixtures of local experts - Jacobs, Jordan, et al. - 1991
537	Neural networks and the bias/variance dilemma - Geman, Bienenstock, et al. - 1992
372	An interactive activation model of context effects in letter perception 1. An account of basic findings - McClelland, Rumelhart - 1981
364	A learning algorithm for Boltzmann machines - Ackley, Hinton - 1985
342	Adaptive pattern classification and universal recoding - Grossberg - 1976
341	Distributed hierarchical processing in the primate cerebral cortex - Felleman, Essen - 1991
336	Simplified neuron model as a principal component analyzer - Oja - 1982
325	What is the goal of sensory coding - Field - 1994
317	On learning the past tense of English verbs - Rumelhart, McClelland - 1986
290	Connectionist Learning Procedures - Hinton - 1990
251	Feature discovery by competitive learning - Rumelhart, Zipser - 1985
218	Theory for the development of neuron selectivity: Orientation specificity and binocular interaction in visual cortex - Bienenstock, Cooper, et al. - 1982
208	Distributed representations - Hinton, McClelland, et al. - 1986
191	Information processing in dynamical systems: Foundations of harmony theory - Smolensky - 1986
187	Unsupervised learning - Barlow - 1989
165	The Helmholtz machine - Dayan, Hinton, et al. - 1995
130	Forming sparse representations by local antiHebbian learning - Földiák - 1990
127	A mean field theory learning algorithm for neural networks - Peterson, Anderson - 1987
125	Generalization by weight–elimination with applications to forecasting - Weigend, Rumelhart, et al. - 1991
122	Interaction of information in word recognition - Morton - 1969
103	Generative models for discovering sparse distributed representations - Hinton, Ghahramani - 1997
88	From rote learning to system building: acquiring verb morphology in children and connectionist nets - Plunkett, Marchman - 1993
77	Overregularization in language acquisition - Marcus, Pinker, et al.
71	Integration of what and where in the primate prefrontal cortex. Science 276: 821–824 - SC, Rainer, et al. - 1997
70	Biologically plausible error-driven learning using local activation differences: the generalized recirculation algorithm - O’Reilly - 1996
70	Maximum likelihood competitive learning - Nowlan - 1990
69	Rethinking infant knowledge: Toward an adaptive process account of successes and failures in object permanence tasks - Munakata, McClelland, et al. - 1997
60	A multiple cause mixture model for unsupervised learning - Saund - 1995
60	Mutual information maximization: Models of cortical self organization - Becker - 1996
57	A back-propagation programmed network that simulates response properties of a subset of posterior parietal neurons. Nature - ZIPSER, RA - 1988
56	Deterministic Boltzmann learning performs steepest descent in weight-space - Hinton - 1990
52	Competition and multiple cause models - Dayan, Zemel - 1995
49	A minimum description length framework for unsupervised learning. Unpublished doctoral dissertation - Zemel - 1993
48	Neural mechanisms of visual processing in monkeys - Desimone, Ungerleider - 1989
42	The recent excitement about neural networks - Crick - 1989
38	Contrastive Hebbian learning in the continuous Hopfield model - Movellan - 1990
38	Category learning through multi-modality sensing - Sa, Ballard - 1998
32	Topography of pyramidal neuron intrinsic connections in macaque monkey prefrontal cortex (areas 9 - Levitt, Lewis, et al. - 1993
32	Learning representation by recirculation - Hinton, McClelland - 1988
24	Testing between the TRACE model and the fuzzy logical model of speech perception - Massaro - 1989
22	S.: A simple neural network exhibiting selective activation of neuronal ensembles: from winner-take-all to winners-share-all - Fukai, Tanaka - 1997
16	A biologically supported error-correcting learning rule - Hancock, Smith, et al. - 1991
15	On reaching - Georgopoulos - 1986
15	Figure-ground organization and object recognition processes: an interactive account - Vecera, O’Reill - 1998
15	Object recognition processes can and do operate before figure-ground organization - Peterson - 1994