GENERALIZATION IN A PERCEPTRON WITH A SIGMOID TRANSFER-FUNCTION
SCIE
- Title
- GENERALIZATION IN A PERCEPTRON WITH A SIGMOID TRANSFER-FUNCTION
- Authors
- HA, S; KANG, K; OH, JH; KWON, C; PARK, Y
- Date Issued
- 1993-12
- Publisher
- KOREAN PHYSICAL SOC
- Abstract
- Learning of layed neural networks is studied using the methods of statistical mechanics. Networks are trained from examples using the Gibbs algorithm. We consider perceptron learning with a sigmoid transfer function. Ising perceptrons, with weights constrained to be discrete, exhibit sudden learning at low temperatures within the annealed approximation. There is a first order transition from a state of poor generalization to a state of perfect generalization. The transition becomes continuous at high temperatures. The analytic results show a good agreement with the computer simulations
- Keywords
- STORAGE CAPACITY; NEURAL NETWORKS; EXAMPLES
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/22005
- ISSN
- 0374-4884
- Article Type
- Article
- Citation
- JOURNAL OF THE KOREAN PHYSICAL SOCIETY, vol. 26, page. S473 - S475, 1993-12
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.