论文信息 - A NP-hardness result for a sigmoidal 3-node neural network - 字舞流文

A NP-hardness result for a sigmoidal 3-node neural network

In this paper we show that the loading problem for a xed neural architecture with sigmoidal activation is NP-hard if the input dimension varies, if the classiication is performed with a certain accuracy, and if the output weights are restricted.

Barbara Hammer | B. Hammer

[1] David S. Johnson,et al. Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[2] Eduardo D. Sontag,et al. Feedforward Nets for Interpolation and Classification , 1992, J. Comput. Syst. Sci..

[3] Mathukumalli Vidyasagar,et al. A Theory of Learning and Generalization , 1997 .

[4] Kurt Hornik,et al. Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[5] Ronald L. Rivest,et al. Training a 3-node neural network is NP-complete , 1988, COLT '88.

[6] Klaus-Uwe Höffgen,et al. Computational Limitations on Training Sigmoid Neural Networks , 1993, Information Processing Letters.

[7] Hava T. Siegelmann,et al. On the complexity of training neural networks with continuous activation functions , 1995, IEEE Trans. Neural Networks.