Abstract: 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 [email protected]. Neural Computing Surveys, http ://www.icsi.berkeley.edu/~ jagota/NCS
Publication Year: 1998
Publication Date: 1998-01-01
Language: en
Type: article
Access and Citation
Cited By Count: 116
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot