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)

The fixed-feature viewpoint Schyns et al. are opposing is not a widely held theoretical position but rather a working assumption of cognitive psychologists – and thus a straw man. We accept their demonstration of new-feature acquisition, but question its ubiquity in category learning. We suggest that new-feature learning (at least in adults) is rarer and more difficult than the authors suggest.

Amit's efforts to provide stronger theoretical and empirical support for Hebb's cell-assembly concept is admirable, but we have serious reservations about the perspective presented in the target article. For Hebb, the cell assembly was a building block; by contrast, the framework proposed here eschews the need to fit the assembly into a broader picture of its function.

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.

In lieu of an abstract, here is a brief excerpt of the content:Eleven brothers and sisters followed me in quick succession and the old farm house was bursting at the seams. So Mom and Dad put on a new dining room. Somehow it didn’t fit. It was built differently than the rest of the house. It was out of place, like a new patch on an old shirt. Some parts of the Later Rule of Saint Francis just don’t fit either. (...) They are “patches,” sewed on afterwards. Those little “patches” on the Later Rule stand out and they tell an important story.In 1221 Saint Francis re-edited the legislation of the Order. At the end of the twenty-four chapters of the new edition of the Rule, he commanded that “on behalf of Almighty God and of the Lord Pope, and by obedience ... that no one delete or add to what has been written in this life” . He would do everything possible to avoid changes, but just a couple of years later there was yet a newer edition of the Rule, which we know as the Later Rule. In his Testament, Francis does not distinguish between these two or, in fact, any of the different stages of the development of the Rule. In spite of the changes, even changes that were not to be expected, it seems that for Francis the Rule is one and the same at whatever stage.The Later Rule consists of twelve chapters. The chapters are not enumerated in the two original manuscripts, but rather are simply distinguished by headings set off from the rest of the text by bold lettering.2 The titles give us the theme of each chapter. It will become obvious to us that the number twelve was intentional and limiting, when we examine the Rule’s “patches” and see that they bring extraneous materials into the twelve chapters of the Rule. By “extraneous” I mean that the materials of the “patches” neither pertain to the principal theme of the chapter of the Later Rule into which they are inserted nor are they drawn from the corresponding chapter of the Earlier Rule. The “patches” do not make a good fit with the chapters in which we find them, but they do have two consistent characteristics: each of them comes at the end of its chapter in the Later Rule and, except for the last of the four patches, each of them includes materials from different chapters of the Earlier Rule. The “patches” we will examine are Chapter III, 10–13; Chapter VI, 7–9; Chapter X, 7–10, and Chapter XII, 3–4. The “patches” shed light on claims that Francis was forced to omit from the Rule ideas that were important to him, and even the myth that the whole original copy of the Rule was intentionally lost. They bring us to the conclusion that nothing important was lost in the transition from the Earlier Rule to the Later Rule.Chapter III, 10–13Chapter three of the Later Rule carries the heading, “The Divine Office, Fasting, and how the Brothers should go about in the World.” Chapter three of the Earlier Rule had also dealt with the divine office and fasting. The earlier text had begun with the saying of the Gospel that some evil spirits could only be driven out “through prayer and fasting” . This Gospel phrase explains why the Later Rule, following the Earlier Rule, deals with prayer and fasting in the same chapter. With respect to the Earlier Rule, Francis has included new content in the corresponding chapter of Later Rule. It is material that goes beyond the themes of prayer and fasting, and it doesn’t mesh neatly with these two themes.Chapter three of the Earlier Rule ends saying, “However, at other times, according to this life, let them not be.. (shrink)