Deep Learning Blindspots

Your browser can't play this video file. Please download the file below and use a desktop player e.g. In the past decade, machine learning researchers and theorists have created deep learning architectures which seem to learn complex topics with little intervention. Newer research in adversarial learning questions just how much "learning" these networks are doing. Several theories have arisen regarding neural network "blind spots" which can be exploited to fool the network.