Effect of Hidden Neuron Size on Different Training Algorithm in Neural Network

We use different types of training algorithms in the neural network. But, we cannot say which kind algorithm is fast for a given problem. So, this survey paper, are trying to find better categorization problems. For purpose, used ten pattern network MATLAB. Levenberg-Marquardt (LM), Bayesian regularization backpropagation (BR), BFGS Quasi-Newton (BFG), Resilient Backpropagation (RP), Scaled Conjugate gradient (SCG), Gradient with Powell/Beale Restarts (CGB), Fletcher-Powell (CGF), Polak-Ribiere (GDM), One Step Secant (OSS), and Variable Learning Rate (GD) algorithm. In also check, affects these on when applied hidden neuron size. During found some new facts. that RP, SCG, CGB, CGF OSS fastest algorithms. BFG takes more time respect GDM GD take epochs. BR not acceptable image categorization.