Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Hankala, Teemu"'
We study the complexity of the problem of training neural networks defined via various activation functions. The training problem is known to be existsR-complete with respect to linear activation functions and the ReLU activation function. We conside
Externí odkaz:
http://arxiv.org/abs/2305.11833
