A connectionist account of the hypothesis of granularity and transparency
0
Citation
0
Reference
10
Related Paper
Keywords:
Granularity
Connectionism
Optical transparency
Connectionism
Symbol (formal)
Cite
Citations (0)
Connectionism
Representation
Cite
Citations (6)
Abstract This is the third volume in the Vancouver Studies in Cognitive Science Series. It is based on a conference that was held in 1990, which was sponsored by the Cognitive Science Program and Linguistics Department of Simon Fraser University. Over the last decade, there has emerged a paradigm of cognitive modeling that has been hailed by many researchers as a radically new and promising approach to cognitive science. This new paradigm has come to be known by a number of names, including “connectionism”, "neural networks", and "parallel distributed processing", (or PDP). This method of computation attempts to model the neural processes that are thought to underlie cognitive functions in human beings. Unlike the digital computation methods used by AI researchers, connectionist models claim to approximate the kind of spontaneous, creative and somewhat unpredicatable behavior of human agents. However, over the last few years, a heated controversy has arisen over the extent to which connectionist models are able to provide successful explanations for higher cognitive processes. A central theme of this book reviews the adequacy of recent attempts to implement higher cognitive processes in connectionist networks.
Connectionism
Theme (computing)
Cite
Citations (108)
Providing coverage of recent research in connectionism, this book contains contributed material from key researchers on a range of topics from biology to hardware, and from psychology to philosophy. It includes chapters on connectionism and the mind-body problem; cognition and nonlinear dynamics; philosophical and theoretical presentation; neural networks and neurocomputing; connectionism and language learning; and neurobiology.
Connectionism
Presentation (obstetrics)
Cite
Citations (2)
Connectionism
Symbol (formal)
Cognitive systems
Cite
Citations (2)
New connectionism is another paradigm reanimated in cognitive psychology in the early 1980s. Compared with the paradigm of symbolic processing of cognitive psychology, the paradigm of new connectionism views mental activity acting as as its metaphor, so it must simulate the brain in the study and adopt the method of structure and function simulating. With the modern means using in the study of brain simulating the brain is no longer a black-box system. Therefore, new connectionism adopts the grey-box method. Because new connectionism regards cognition mainly as the mass property emerging from the reaction of neural network, it must adopt the tactics of mass reductionism. On the guide of the methodology,the study of connectionism should shed more light on the nature of mind.
Connectionism
Reductionism
Cite
Citations (1)
This is not the place to present an introduction to connectionism, an approach to modeling cognitive phenomena that was first developed in the 1950s and once again gained prominence in the 1980s, in part with the publication of Rumelhart, McClelland, and the PDP Research Group (1986). Both Paul and Patricia Churchland have presented introductions to connectionism in various of their writings. See also Bechtel and Abrahamsen (1991) for an introduction. The understanding of connectionism varies significantly among authors. For both of the Churchlands the importance of connectionism seems to be that the parallels between connectionist networks and real neural networks allows our emerging understanding of brain function to inform cognitive modeling. For many others the importance lies not so much in the similarity of connectionist networks to neural architecture as in the fact that connectionist models seem to exhibit features of cognition lacking in other approaches to cognitive modeling.
Connectionism
Similarity (geometry)
Cite
Citations (32)
Abstract Connectionists claim that human cognitive computational architecture is connectionist. Proponents of classical computational architectures have challenged this claim, arguing that a pervasive feature of human cognition, its ‘systematicity’, cannot be explained in connectionist terms.
Connectionism
Feature (linguistics)
Cognitive systems
Cite
Citations (2)
Connectionist research is rmly established within the scienti c community, especially within the multi-disciplinary eld of cognitive science. This diversity, however, has created an environment which makes it di cult for connectionist researchers to remain aware of recent advances in the eld, let alone understand how the eld has developed. This paper attempts to address this problem by providing a brief guide to connectionist research. The paper begins by de ning the basic tenets of connectionism. Next, the development of connectionist research is traced, commencing with connectionism's philosophical predecessors, moving to early psychological and neuropsychological in uences, followed by the mathematical and computing contributions to connectionist research. Current research is then reviewed, focusing speci cally on the di erent types of network architectures and learning rules in use. The paper concludes by suggesting that neural network research|at least in cognitive science|should move towards models that incorporate the relevant functional principles inherent in neurobiological systems. 1 The Connectionist Revolution This solution takes the form of a new associationism, or better, since it di ers deeply and widely from that older British associationism, of a new connectionism. ([109], p. 4) Connectionist research is rmly established within the scienti c community. Researchers can be found in such elds as arti cial intelligence [33][1], cognitive neuroscience [76], economics [117][121], linguistics [84], philosophy [48], and physics [47] to name but a few. It has even been suggested that connectionism represents a Kuhnian-like paradigm shift for psychology [98]. But, perhaps the eld that has most bene ted from connectionist research is the multidisciplinary eld of cognitive science [8][19][96][69][108]. As Hanson and Olson have stated: \The neural network revolution has happened. We are living in the aftermath ([42], p. 332). Unfortunately, this revolution has created an environment in which researchers may nd it di cult to keep up with recent advances in neural network research. Furthermore, the history of connectionist research is often overlooked, or at least misconstrued [81]. As a result, a view popular with current researchers is that connectionism really emerged in the 1980's|there is only brief mention of research before that time (e.g., [8], [48]). Connectionism, however, has a very long past. In fact, one can trace the origin of connectionist ideas to the early Greek philosopher, Aristotle, and his ideas on mental associations. These ideas were elaborated by the British empiricists and then naturally extended by the founders of psychology. Neuropsychologists This work was supported by a Killam Scholarship. The author is now at the Center for the Neural Basis of Cognition, Carnegie Mellon University, Pittsburgh, PA. Updates, corrections, and comments should be sent to David A. Medler at medler@cnbc.cmu.edu. Neural Computing Surveys, http ://www.icsi.berkeley.edu/~ jagota/NCS
Connectionism
Cite
Citations (123)
Connectionist models have come to play an important role in cognitive science and in cognitive neuroscience, yet their role in explaining behavior is not necessarily obvious and has generated considerable debate. Connectionism is a body of tools and ideas that can be used in different ways. It can be treated as a form of simulation modeling in which the goal is to implement preexisting theories. In this approach, connectionist models function as a kind of statistical tool, a way of analyzing a complex set of data. Connectionism can also be seen as providing a small set of general theoretical principles that apply in a variety of domains. Construed in this way, it contributes to the development of theories that are explanatory, not merely descriptive.
Connectionism
Cite
Citations (114)