Reinforcement Learning with TensorFlow

The vanishing gradient problem

The vanishing gradient problem is one of the problems associated with the training of artificial neural networks when the neurons present in the early layers are not able to learn because the gradients that train the weights shrink down to zero. This happens due to the greater depth of neural network, along with activation functions with derivatives resulting in low value.

Try the following steps:

1. Create one hidden layer neural network
2. Add more hidden layers, one by one

We observe the gradient with regards to all the nodes, and find that the gradient values get relatively smaller when we move from the later layers to the early layers. This condition worsens with the further addition of layers. This shows that ...