"0899-7667" . "2709;2729" . "[56AA68048A7F]" . . "Training a Single Sigmoidal Neuron is Hard." . "N/A" . "20"^^ . . . "US - Spojen\u00E9 st\u00E1ty americk\u00E9" . "Training a Single Sigmoidal Neuron is Hard."@en . . "\u0160\u00EDma, Ji\u0159\u00ED" . . "sigmoidal neuron; loading problem; NP-hardness"@en . . "14" . . . . . "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,beta], 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..." . "Training a Single Sigmoidal Neuron is Hard." . . . "667207" . . "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,beta], 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..."@en . . "Training a Single Sigmoidal Neuron is Hard."@en . . . "RIV/67985807:_____/02:06020147!RIV/2003/AV0/A06003/N" . "P(LN00A056), Z(AV0Z1030915)" . "1"^^ . . "RIV/67985807:_____/02:06020147" . "0"^^ . "1"^^ . "0"^^ . "Neural Computation" .