Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Holenda, Slavomír"'
Classical neural networks achieve only limited convergence in hard problems such as XOR or parity when the number of hidden neurons is small. With the motivation to improve the success rate of neural networks in these problems, we propose a new neura
Externí odkaz:
http://arxiv.org/abs/2401.06137
