In the standard 3 layer net, there are 3 weight matrices: one before layer 1; one before layer 2; and one before layer 3. I would like to either eliminate the weight matrix before layer 1 (the IW matrix) or set it so that its weights are the identity matrix AND they will not be modified during training.
MATLAB: How to eliminate or ignore the weight matrix before layer one during training of a neural network
Deep Learning Toolboxiwmatrix
Related Question
- How to create a neural network with 1 layer only (no hidden layers)
- How to use this code.
- How to train ann with multiple input data
- Error in Alexnet layer replacement
- Neural network about weights
- Neural network weight and bias initializaiton problem
- Can I use NN built with Fitnet for Reinforcement Learning toolbox with DQN agent
Best Answer