Search results for "connectionism"
showing 10 items of 21 documents
What represents a face? A computational approach for the integration of physiological and psychological data.
1997
Empirical studies of face recognition suggest that faces might be stored in memory by means of a few canonical representations. The nature of these canonical representations is, however, unclear. Although psychological data show a three-quarter-view advantage, physiological studies suggest profile and frontal views are stored in memory. A computational approach to reconcile these findings is proposed. The pattern of results obtained when different views, or combinations of views, are used as the internal representation of a two-stage identification network consisting of an autoassociative memory followed by a radial-basis-function network are compared. Results show that (i) a frontal and a…
Connectionist models of face processing: A survey
1994
Abstract Connectionist models of face recognition, identification, and categorization have appeared recently in several disciplines, including psychology, computer science, and engineering. We present a review of these models with the goal of complementing a recent survey by Samal and Iyengar [Pattern Recognition25, 65–77 (1992)] of nonconnectionist approaches to the problem of the automatic face recognition. We concentrate on models that use linear autoassociative networks, nonlinear autoassociative (or compression) and/or heteroassociative backpropagation networks. One advantage of these models over some nonconnectionist approaches is that analyzable features emerge naturally from image-b…
Panel Summary: Symbolism and Connectionism Paradigms
1999
The aim of this chapter is to report the panel discussion on symbolism and connectionism paradigms. In particular, the following hot point are analysed: what cognitive phenomena are most difficult for connectionists to explain? what cognitive phenomena are most naturally explained in connectionist terms? is symbolic deduction a central kind of human thinking? How do people make deductions? is nondeductive reasoning done in accord with the laws of probability? what areas of knowledge do you have that are easily described in terms of symbolic rules? concepts reduced to rules, concepts reduced to networks; symbolic and connectionist mechanisms of analogy; planning, decision, explanation, learn…
Shallow Reductionism and the Problem of Complexity in Psychology
2008
In his recent book The Mind Doesn't Work That Way, Fodor argues that computational modeling of global cognitive processes, such as abductive everyday reasoning, has not been successful. In this article the problem is analyzed in the framework of algorithmic information theory. It is argued that the failed approaches are characterized by shallow reductionism, which is rejected in favor of deep reductionism and nonreductionism.
Relational priming is to analogy-making as one-ball juggling is to seven-ball juggling
2008
Relational priming is argued to be a deeply inadequate model of analogy-making because of its intrinsic inability to do analogies where the base and target domains share no common attributes and the mapped relations are different. The authors rely on carefully handcrafted representations to allow their model to make a complex analogy, seemingly unaware of the debate on this issue 15 years ago. Finally, they incorrectly assume the existence of fixed, context-independent relations between objects. Although relational priming may indeed play some role in analogy-making, it is an enormous – and unjustified – stretch to say that it is “centrally implicated in analogical reasoning” (sect. 2, para…
The Stability-Plasticity Dilemma: Investigating the Continuum from Catastrophic Forgetting to Age-Limited Learning Effects
2013
The stability-plasticity dilemma is a well-know constraint for artificial and biological neural systems. The basic idea is that learning in a parallel and distributed system requires plasticity for the integration of new knowledge, but also stability in order to prevent the forgetting of previous knowledge. Too much plasticity will result in previously encoded data being constantly forgotten, whereas too much stability will impede the efficient coding of this data at the level of the synapses. However, for the most part, neural computation has addressed the problems related to excessive plasticity or excessive stability as two different fields in the literature.
A system based on neural architectures for the reconstruction of 3-D shapes from images
1991
The connectionist approach to the recovery of 3-D shape information from 2-D images developed by the authors, is based on a system made up by two cascaded neural networks. The first network is an implementation of the BCS, an architecture which derives from a biological model of the low level visual processes developed by Grossberg and Mingolla: this architecture extracts a sort of brightness gradient map from the image. The second network is a backpropagation architecture that supplies an estimate of the geometric parameters of the objects in the scene under consideration, starting from the outputs of the BCS. A detailed description of the system and the experimental results obtained by si…
Effects of Global and Local Contexts on Harmonic Expectancy
1998
Several psycholinguistic studies have investigated the influence of local and global semantic contexts on word processing. The first aim of the present study was to examine local and global level contributions to harmonic priming. The second was to test a spreading-activation account of harmonic context effects (Bharucha, 1987). The expectations for the last chord (the target) of eight-chord sequences were varied by simultaneously manipulating the harmonic relationship of the target to the first six chords (global context) and to the seventh chord (local context). Human performances demonstrated that harmonic expectancies are derived from both the global and local levels of musical structur…
Conceptual Spaces for Cognitive Architectures: A lingua franca for different levels of representation
2017
During the last decades, many cognitive architectures (CAs) have been realized adopting different assumptions about the organization and the representation of their knowledge level. Some of them (e.g. SOAR [Laird (2012)]) adopt a classical symbolic approach, some (e.g. LEABRA [O'Reilly and Munakata (2000)]) are based on a purely connectionist model, while others (e.g. CLARION [Sun (2006)] adopt a hybrid approach combining connectionist and symbolic representational levels. Additionally, some attempts (e.g. biSOAR) trying to extend the representational capacities of CAs by integrating diagrammatical representations and reasoning are also available [Kurup and Chandrasekaran (2007)]. In this p…
Coarse scales are sufficient for efficient categorization of emotional facial expressions: Evidence from neural computation
2010
The human perceptual system performs rapid processing within the early visual system: low spatial frequency information is processed rapidly through magnocellular layers, whereas the parvocellular layers process all the spatial frequencies more slowly. The purpose of the present paper is to test the usefulness of low spatial frequency (LSF) information compared to high spatial frequency (HSF) and broad spatial frequency (BSF) visual stimuli in a classification task of emotional facial expressions (EFE) by artificial neural networks. The connectionist modeling results show that an LSF information provided by the frequency domain is sufficient for a distributed neural network to correctly cla…