Implementation of Artificial Neural Networks in MATLAB


This video tutorial is the second part of the complete course of deep learning in MATLAB. We recommend you to order the complete course to learn completely.




Neural network programming in MATLAB software

Preprocessing and post-processing

(Mapminamx, Mapstd, Processpca, Fixunknowns, and removeconstraints)

Normalize input data

Correction of unmissed data unmissed values

Neural Network App

(nftool, nctool, nprtool and ntstool)

Multilayer Shallow Neural Networks

Neural network commands in MATLAB

(feedforwardnet, cascadeforwardnet, fitnet, patternnet)

Neural network for fitting application

Neural network for pattern recognition application

Neural Network Object Properties

(net.biasConnect, net.inputConnect, net.layerConnect, net.outputConnect , net.biases, net.inputWeights, net.layerWeights , net.outputs, net.IW , net.LW, net.b)

Weight and Bias Values

Neural Network Subobject Properties

( Inputs, Layers, Outputs, Biases, Input Weights, Layer Weights)

Adjust the number of neurons in the hidden layer

Set the neural network training function

Neural network modeling

Select the training function

Which training function should we choose to train the neural network?

What is the difference between trainlm, trainbr and trainscg? Which one is better?

Familiarity with training functions
(traingd, traingdm, traingda, traingdx, trainrp, traincgf, traincgp, traincgb, trainscg, trainbfg, trainoss, trainlm, and trainbr)

What is the most used neural network training function?

Is rapid convergence good?

Neural Networks with Parallel and GPU Computing

Autoencoder class

Learning vector quantization neural network


Self-organizing map

Competitive Neural Network

Kohonen Learning Rule (learnk)

Bias Learning Rule (learncon)





There are no reviews yet.

Be the first to review “Implementation of Artificial Neural Networks in MATLAB”

Your email address will not be published. Required fields are marked *