Early neural network development history: the age of Camelot
Russell C. Eberharta b, Roy W. Dobbinsb c
- aAppl. Phys. Lab., Johns Hopkins Univ., Laurel, MD
- bAppl. Phys. Lab. Johns Hopkins Univ., Laurel, MD, USA
- cAppl. Phys. Lab., Johns Hopkins Univ., Laurel, MD, USA
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
What the authors refer to as the first of four ages in the development of neural networks is discussed. It begins about a century ago with the American psychologist William James, and ends in 1969 with the publication of the book by M. Minsky and S. Papert on perceptrons. The history of this period is reviewed, focusing on people rather than just on theory or technology. The contributions of a number of individuals are discussed and related to how neural network tools are being implemented today. The selection of individuals discussed is somewhat arbitrary and not exhaustive, as the intent is to provide a broad sampling of people who contributed to current neural network technology. Besides James, the authors cover the work of W.C. McCulloch and W. Pitts (1943), D. Hebb (1949), and B. Widrow and M. Hoff (1960).