What question did this study set out to answer?

This research aims to develop a statistical framework for learning in layered neural networks and to evaluate generalization capabilities.

A statistical approach to learning and generalization in layered neural networks

View Full Paper

Ask AI

Bookmark

Authors

Randomized approach finds optimal architecture and predicts learning curves for neural networks, indicating effectiveness.

This research aims to develop a statistical framework for learning in layered neural networks and to evaluate generalization capabilities.
Presents a statistical description of learning from examples in neural networks.
Derives the Gibbs distribution for networks with fixed architecture to analyze performance.
Utilizes entropy to measure the prediction distribution in terms of network performance.
Establishes a connection between minimum error and maximum likelihood criteria for neural networks.
Finds that the Gibbs distribution provides a reliable measure for the generalization ability of networks.
Shows that entropy effectively quantifies network performance in terms of prediction accuracy.

Levin et al. (1990) studied this question.

View Full Paper

Ask AI

Bookmark