Performance of Neural Networks Having Non-Monotonous Activation Functions
Manabu Kotani, Haruya Matsumoto, Toshihide KANAGAWA · Transactions of the Society of Instrument and Control Engineers · 1993
The performance of neural networks having a non-monotonous activation function is described.The possibility to improve two difficulties, convergence to local minima and slow learning speed, is examined.Simulations are performed for the exclusive-or and the binary addition problems.The network is also applied to the acoustic diagnosis for a compressor as a practical pattern recognition task.The obtained results show that the three-layered neural networks having the non-monotonous activation function are effective for the above problems and have the same generalization performance as the three-layered network having the sigmoidal activation function.