论文信息 - On the computational capability of a perceptron

On the computational capability of a perceptron

The minimal fraction of errors a perceptron can make on P random dichotomies is investigated. An exact upper bound is presented as well as comparisons between the replica theory estimates and a rigorous lower bound.

José F. Fontanari | W K Theumann

[1] G. Parisi. The order parameter for spin glasses: a function on the interval 0-1 , 1980 .

[2] Thomas M. Cover,et al. Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition , 1965, IEEE Trans. Electron. Comput..

[3] Demetri Psaltis,et al. On Reliable Computation With Formal Neurons , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4] D. Thouless,et al. Stability of the Sherrington-Kirkpatrick solution of a spin glass model , 1978 .

[5] E. Gardner,et al. Optimal storage properties of neural network models , 1988 .

[6] R. Erichsen,et al. Optimal storage of a neural network model: a replica symmetry-breaking solution , 1993 .

[7] J. Nadal,et al. Information capacity of a perceptron , 1992 .

[8] E. Gardner. The space of interactions in neural network models , 1988 .

[9] S. Kirkpatrick,et al. Solvable Model of a Spin-Glass , 1975 .