In the first section of the article, we examine some recent criticisms of the connectionist enterprise: first, that connectionist models are fundamentally behaviorist in nature (and, therefore, non-cognitive), and second that connectionist models are fundamentally associationist in nature (and, therefore, cognitively weak). We argue that, for a limited class of connectionist models (feed-forward, pattern-associator models), the first criticism is unavoidable. With respect to the second criticism, we propose that connectionist modelsare fundamentally associationist but that this is appropriate for building models (...) of human cognition. However, we do accept the point that there are cognitive capacities for which any purely associative model cannot provide a satisfactory account. The implication that we draw from is this is not that associationist models and mechanisms should be scrapped, but rather that they should be enhanced.In the next section of the article, we identify a set of connectionist approaches which are characterized by “active symbols” — recurrent circuits which are the basis of knowledge representation. We claim that such approaches avoid criticisms of behaviorism and are, in principle, capable of supporting full cognition. In the final section of the article, we speculate at some length about what we believe would be the characteristics of a fully realized active symbol system. This includes both potential problems and possible solutions (for example, mechanisms needed to control activity in a complex recurrent network) as well as the promise of such systems (in particular, the emergence of knowledge structures which would constitute genuine internal models). (shrink)
Rachlin's thought-provoking analysis could be strengthened by greater openness to evolutionary interpretation and the use of the directed attention concept as a component of self-control. His contribution to the understanding of prosocial behavior would also benefit from abandoning the traditional (and excessively restrictive) definition of altruism.
The Advaita Vedānta notion of ātman/Brahman presents serious philosophical challenge to this school—namely, it demands that they explain how all can be undivided, unchanging, and pure consciousness, yet appear to be everything but nondual, unchanging, and pure consciousness. The Advaita answer is avidyā, ajñāna. This answer tells us that Brahman does not really change; it is only ignorance that makes it appear to change. This answer has engendered as many questions as it has resolved, and it is possible that they (...) can be boiled down to the following: how can vidyā and avidyā be simultaneous and coterminous? After reviewing the Advaita responses to the debates regarding avidyā which arose within Advaita and between Advaitins and their opponents, traditional Advaita path will be followed by offering an analogy to illuminate this quandary. The strength of this contemporary analogy, based on holography, lies in its ability to illuminate the nature of Brahman as being without parts, without duality, without change; yet holography presents us with images that appear to change and be with parts. (shrink)
Krishnachandra Bhattacharyya, one of the preeminent Indian philosophers of the 20th century, proposed that the absolute appears in three alternative forms - truth, freedom and value. Each of these forms are for Bhattacharyya absolute, ultimate, not penultimate. Each is different from the other, yet they cannot be said to be one or many. He contends that these absolutes are incompatible with each other and that an articulation of the relation between the three absolutes is not feasible. This paper will review (...) Bhattacharyya 's presentation of the absolute in its alternative forms and will place these abstractions within the context of three specific religious traditions that he sees illustrating his point. Then, using a model based upon holography, I will illuminate with 'concrete images' that which Bhattacharyya could deductively formulate but could not logically integrate. Holography, the process by which three-dimensional images are produced from an imageless film - a film in which each part can reproduce the whole - will be used as a heuristic device to illuminate the simultaneous and mutually interpenetrating existence of the absolute in three forms. This model will illumine how these three forms can be conceived of as not the same yet not other and how these forms can be incompatible as absolutes, but metaphysically inseparable. (shrink)
Perceptual learning mechanisms derived from Hebb's theory of cell assemblies can generate prototypic representations capable of extending the representational power of TEC (Theory of Event Coding) event codes. The extended capability includes categorization that accommodates “family resemblances” and problem solving that uses cognitive maps.
Abstract Daniel H. H. Ingalls referred to Gaudap?da's M?nd?kya K?rik?, a very early Advaita text, as ? ... the most puzzling perhaps, of all Sanskrit philosophical texts?. This article shows that some of the philosophical quandaries associated with this text are the result of inappropriately imposing a graphic and prose model of textuality upon a text composed in the k?rik? (memorial verse) genre and in an oral cultural context. Developing a model of textuality consistent with the literary genre and cultural (...) context, the article is not only able to resolve some of the philosophical problems associated with the text, but also raises the possibility that this inappropriate hermeneutical process has contributed to mislabelling Gaudap?da as an idealist. (shrink)
Page's target article makes a good case for the strength of localist models. This can be characterized as an issue of where new information is integrated with respect to existing knowledge structures. We extend the analysis by discussing the dimension of when this integration takes place, the implications, and how they guide us in the creation of cognitive models.
The Advaita Vedānta notion of ātman/Brahman presents a serious philosophical challenge to this school-namely, it demands that they explain how all (reality) can be undivided, unchanging, and pure consciousness, yet appear to be everything but nondual, unchanging, and pure consciousness. The Advaita answer is avidyā, ajāna (ignorance). This answer tells us that Brahman does not really change; it is only ignorance that makes it appear to change. This answer has engendered as many questions as it has resolved, and it is (...) possible that they can be boiled down to the following: how can vidyā and avidyā be simultaneous and coterminous? After reviewing the Advaita responses to the debates regarding avidyā, which arose within Advaita and between Advaitins and their opponents, a traditional Advaita path will be followed by offering an analogy to illuminate this quandary. The strength of this contemporary analogy, based on holography, lies in its ability to illuminate the nature of Brahman as being without parts, without duality, without change; yet holography presents us with images that appear to change and be with parts. (shrink)
Pulvermüller's work in extending Hebb's theory into the realm of language is exciting. However, we feel that what he characterizes as a single cell assembly is actually a set of cooperating cell assemblies that form parts of larger cognitive structures. These larger structures account more easily for a variety of phenomena, including the psycholinguistic.
This paper articulates an infusion model of ethics education for engineering students by illuminating the value of a religious studies course on yoga. This model is distinguished from four other possible approaches that have traditionally been used to prepare engineering students to face the challenges of the work place. The article is not claiming that this approach should be used to the exclusion of the other approaches, but rather that it adds strength to the other approaches. Specifically, the article claims (...) that the infusion model provides an opportunity for students to reflect upon the foundational ethical positions emanating from the world’s religions and thereby provides them with a vista from which they can not only ask what professional ethical code applies in a given situation, but also ponder the nature of character needed to follow that ethical code. (shrink)
We propose a way in which Barsalou could strengthen his position and at the same time make a considerable dent in the category/abstraction problem (that he suggests remains unsolved). There exists a class of connectionist models that solves this problem parsimoniously and provides a mechanistic underpinning for the promising high-level architecture he proposes.
Although Glenberg 's theory benefits from the incorporation of a suppression concept, a more differentiated view of suppression would be even more effective. We propose such a concept, showing how it accounts for phenomena that Glenberg describes and also for phenomena that he ignores.