Approximation theory of the MLP model in neural networks
- 1 January 1999
- journal article
- research article
- Published by Cambridge University Press (CUP) in Acta Numerica
- Vol. 8, 143-195
- https://doi.org/10.1017/s0962492900002919
Abstract
In this survey we discuss various approximation-theoretic problems that arise in the multilayer feedforward perceptron (MLP) model in neural networks. The MLP model is one of the more popular and practical of the many neural network models. Mathematically it is also one of the simpler models. Nonetheless the mathematics of this model is not well understood, and many of these problems are approximation-theoretic in character. Most of the research we will discuss is of very recent vintage. We will report on what has been done and on various unanswered questions. We will not be presenting practical (algorithmic) methods. We will, however, be exploring the capabilities and limitations of this model.Keywords
This publication has 106 references indexed in Scilit:
- Identifying Linear Combinations of Ridge FunctionsAdvances in Applied Mathematics, 1999
- Degree of Approximation by Neural and Translation Networks with a Single Hidden LayerAdvances in Applied Mathematics, 1995
- Neural Networks for Localized ApproximationMathematics of Computation, 1994
- Fundamentality of Ridge FunctionsJournal of Approximation Theory, 1993
- Letters to the editorNeural Networks, 1993
- Theory of the backpropagation neural networkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Universal approximation using feedforward networks with non-sigmoid hidden layer activation functionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Construction of neural nets using the radon transformPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- There exists a neural network that does not make avoidable mistakesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Capabilities of three-layered perceptronsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988