e-space
Manchester Metropolitan University's Research Repository

Neural Networks and the Bias/Variance Dilemma

Geman, S and Bienenstock, E and Doursat, R (1992) Neural Networks and the Bias/Variance Dilemma. Neural Computation, 4. ISSN 0899-7667

Full text not available from this repository.

Abstract

Feedforward neural networks trained by error backpropagation are examples of nonparametric regression estimators. We present a tutorial on nonparametric inference and its relation to neural networks, and we use the statistical viewpoint to highlight strengths and weaknesses of neural models. We illustrate the main points with some recognition experiments involving artificial data as well as handwritten numerals. In way of conclusion, we suggest that current-generation feedforward neural networks are largely inadequate for difficult problems in machine perception and machine learning, regardless of parallel-versus-serial hardware or other implementation issues. Furthermore, we suggest that the fundamental challenges in neural modeling are about representation rather than learning per se. This last point is supported by additional experiments with handwritten numerals.

Impact and Reach

Statistics

Downloads
Activity Overview
2Downloads
603Hits

Additional statistics for this dataset are available via IRStats2.

Altmetric

Actions (login required)

Edit Item Edit Item