Training a Single Sigmoidal Neuron is Hard

0404583 - UIVT-O 20020147 RIV US eng J - Journal Article
Šíma, Jiří
Training a Single Sigmoidal Neuron is Hard.
Neural Computation. Roč. 14, č. 11 (2002), s. 2709-2729. ISSN 0899-7667. E-ISSN 1530-888X
R&D Projects: GA MŠMT LN00A056
Keywords : sigmoidal neuron * loading problem * NP-hardness
Subject RIV: BA - General Mathematics
Impact factor: 2.313, year: 2002

We first present a brief survey of hardness results for training feedforward neural networks. These results are then completed by the proof that the simplest architecture containing only a single neuron that applies a sigmoidal activation function \sigma:R-->[\alpha,ta], satisfying certain natural axioms, e.g. the standard (logistic) sigmoid or saturated-linear function, to the weighted sum of $n$ inputs is hard to train. In particular, the problem of finding the weights of such a unit that minimize...
Permanent Link: http://hdl.handle.net/11104/0124828