Recent years have produced great advances in training large, deep neural networks (DNNs), including notable successes in training convolutional neural networks (convnets) to recognize natural images. However, our understanding of how these models work, especially what computations they perform at intermediate layers, has lagged behind. Here we introduce two tools for better visualizing and interpreting neural nets. The first is a set of new regularization methods for finding preferred activations using optimization, which leads to clearer and more interpretable images than had been found before. The second tool is an interactive toolbox that visualizes the activations produced on each layer of a trained convnet. You can input image files or read video from your webcam, which we’ve found fun and informative. Both tools are open source.

Video tour of the Deep Visualization Toolbox. Best in HD!Conference: Deep Learning workshop at ICML 2015. Oral presentation.

Press coverage:

• The Verge. Artificial intelligence is going to make it easier than ever to fake images and video
• Nvidia. Harnessing the Caffe Framework for Deep Visualization
• Motherboard. This Is What Actually Happens When a Computer ‘Dreams’
• American Scientist. Computer Vision and Computer Hallucinations