Title :
On training with slope adaptation for feedforward NNs
Author :
Mandic, Danilo P. ; Krcmar, Igor R.
Author_Institution :
Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
Abstract :
Relationships between the learning rate η and the slopes β in the tanh activation function for a feedforward neural network (NN) are provided. The analysis establishes the equivalence in the static and dynamic sense between a referent and an arbitrary feedforward NN which helps to reduce the number of degrees of freedom in learning algorithms for NNs
Keywords :
backpropagation; feedforward neural nets; multilayer perceptrons; transfer functions; degrees of freedom; learning rate; slope adaptation; tanh activation function; training; Algorithm design and analysis; Backpropagation algorithms; Computational complexity; Error correction; Feedforward neural networks; Neural networks; Neurons; Process control; Signal processing algorithms; System identification;
Conference_Titel :
Neural Network Applications in Electrical Engineering, 2000. NEUREL 2000. Proceedings of the 5th Seminar on
Conference_Location :
Belgrade
Print_ISBN :
0-7803-5512-1
DOI :
10.1109/NEUREL.2000.902381
