论文信息 - Training a sigmoidal network is difficult

Training a sigmoidal network is difficult

In this paper we show that the loading problem for a node architecture with sigmoidal activation is NP hard if the input dimension varies if the classi cation is performed with a certain accuracy and if the output weights are restricted

Barbara Hammer | B. Hammer

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

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

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

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

[5] Van H. Vu. On the Infeasibility of Training Neural Networks with Small Squared Errors , 1997, NIPS.

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