DeepEyes: Progressive Visual Analytics for Designing Deep Neural Networks

DeepEyes is a Progressive Visual Analytics system from TU Delft for the analysis of deep neural networks during training. The overview on the training is given by the commonly used loss- and accuracy-curves (a) and the Perplexity Histograms (b) a novel visualization that allows the detection of stable layers. A detailed analysis per layer is performed in three tightly linked visualizations. Degenerated filters are detected in the Activation Heatmap (c), and filter activations are visualized on the Input Map (d). Finally, in the Filter Map (e), relationships among the filters in a layer are visualized.


Want to receive more content like this in your inbox?