Selected bibliography on connectionism

作者: Oliver G Selfridge , Richard S Sutton , Charles W Anderson

DOI:

关键词:

摘要: The topic of this annotated bibliography is connectionism, a field of computer science that has enjoyed a vast resurgence in the last ten years. Properly speaking, connectionism should be regarded as part of Artificial Intelligence, or AI, and up to some years ago it was usually so treated. The earlier entries below will make that clear. Another term for connectionism is Neural Networks, and it is being widely used, especially among the new efforts that are arising, including start-up companies.Connectionism has two chief interests: one is the efficiency or novelty of certain kinds of computation; the other is models of real brains or real neural networks—the kinds made of flesh. The former is our concern here. It has been claimed that connectionism can exhibit a new kind of computing, which is" non-von-Neumann," and can thereby provide new capabilities that cannot be matched in other ways. We want to point readers towards publications that can give them background and insights about the real issues and the state of the field and its prospects. We do not cover the recent work on implementation technologies. Our audience here is anybody who wants or needs more than buzzword knowledge about the field, including researchers, students, and managers in computer science and technology.

参考文章(0)