1997/08/21 by U. Bastolla, U Bastolla, G Parisi +1 · 14 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Physics and Astronomy · #Artificial neural network #Attractor #Cellular neural network #Neural Networks and Applications #Stability (learning theory) #Statistical Mechanics and Entropy #Statistical model #Stochastic Gradient Optimization Techniques #Stochastic neural network #cond-mat.dis-nn #q-bio
paper · pdf · doi:10.1088/0305-4470/30/16/007
published in Journal of Physics A Mathematical and General 30(16), 5613-5631 (Institute of Physics) · 23 pages, 6 figures, Latex, to appear on J. Phys. A
openalex publication_date 1997/08/21 · arxiv created 1997/08/28 · arxiv updated 2009/11/30 · openalex created_date 2016/06/24 · openalex updated_date 2026/08/05
The statistical properties of the length of the cycles and of the weights of the attraction basins in fully asymmetric neural networks (i.e. with completely uncorrelated synapses) are computed in the framework of the annealed approximation which we previously introduced for the study of Kauffman networks. Our results show that this model behaves essentially as a random map possessing a reversal symmetry. Comparison with numerical results suggests that the approximation could become exact in the large-size limit.