Correlation of internal representations in feed-forward neural networks

Abstract

Feed-forward multilayer neural networks implementing random input-output mappings develop characteristic correlations between the activity of their hidden nodes which are important for the understanding of the storage and generalization performance of the network. It is shown how these correlations can be calculated from the joint probability distribution of the aligning fields at the hidden units for arbitrary decoder function between hidden layer and output. Explicit results are given for the parity-, and-, and committee-machines with arbitrary number of hidden nodes near saturation.

6 pages, latex, 1 figure

References in corpus (1)

• Weight Space Structure and Internal Representations: a Direct Approach to Learning and Generalization in Multilayer Neural Network

Cited by in corpus (7)

• Techniques of replica symmetry breaking and the storage problem of the McCulloch-Pitts neuron
• Analytical and Numerical Study of Internal Representations in Multilayer Neural Networks with Binary Weights
• Storage capacity of correlated perceptrons
• Correlations between hidden units in multilayer neural networks and replica symmetry breaking
• Statistical mechanics of extensive-width Bayesian neural networks near interpolation
• Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolation
• Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation