Learning capability and storage capacity of two-hidden-layer feedforward networks
Top Cited Papers
- 26 March 2003
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 14 (2) , 274-281
- https://doi.org/10.1109/tnn.2003.809401
Abstract
The problem of the necessary complexity of neural networks is of interest in applications. In this paper, learning capability and storage capacity of feedforward neural networks are considered. We markedly improve the recent results by introducing neural-network modularity logically. This paper rigorously proves in a constructive method that two-hidden-layer feedforward networks (TLFNs) with 2/spl radic/(m+2)N (/spl Lt/N) hidden neurons can learn any N distinct samples (x/sub i/, t/sub i/) with any arbitrarily small error, where m is the required number of output neurons. It implies that the required number of hidden neurons needed in feedforward networks can be decreased significantly, comparing with previous results. Conversely, a TLFN with Q hidden neurons can store at least Q/sup 2//4(m+2) any distinct data (x/sub i/, t/sub i/) with any desired precision.Keywords
This publication has 22 references indexed in Scilit:
- The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the networkIEEE Transactions on Information Theory, 1998
- Sample sizes for sigmoidal neural networksPublished by Association for Computing Machinery (ACM) ,1995
- Neural networks, approximation theory, and finite precision computationNeural Networks, 1995
- Approximation capability in C(R~/sup n/) by multilayer feedforward networks and related problemsIEEE Transactions on Neural Networks, 1995
- Constructive neural networks with piecewise interpolation capabilities for function approximationsIEEE Transactions on Neural Networks, 1994
- The Lower Bound of the Capacity for a Neural Network with Multiple Hidden LayersPublished by Springer Nature ,1993
- Multilayer feedforward networks with a nonpolynomial activation function can approximate any functionNeural Networks, 1993
- Approximation of continuous functions on Rd by linear combinations of shifted rotations of a sigmoid function with and without scalingNeural Networks, 1992
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- On the capabilities of multilayer perceptronsJournal of Complexity, 1988