Quantcast
Channel: Classification with feed forward network in Matlab strange results? - Stack Overflow
Browsing all 2 articles
Browse latest View live

Answer by Diphtong for Classification with feed forward network in Matlab...

The tansig activation function essentially makes it possible than a neuron becomes inactive due to saturation. A linear neuron is always active. Therefore if one linear neuron has bad parameters, it...

View Article



Classification with feed forward network in Matlab strange results?

I have ran some classification tests in Matlab with feed forward network. Using the standard tansig function the results were better when using more neurons on the hidden layer. But, when I switched...

View Article
Browsing all 2 articles
Browse latest View live




Latest Images