RNNbow: Visualizing Learning Via Backpropagation Gradients in RNNs
Dylan Cashman, Genevieve Patterson, Ab Mosca, Nathan Watts, Shannon Robinson, Remco Chang · IEEE Computer Graphics and Applications · 2018
We present RNNbow, an interactive tool for visualizing the gradient flow during backpropagation in training of recurrent neural networks. By visualizing the gradient, as opposed to activations, RNNbow offers insight into how the network is learning. We show how it illustrates the vanishing gradient and the training process.