Pruning AI networks without impacting performance

In a spotlight paper from the 2017 NIPS Conference, my team and I presented an AI optimization framework we call Net-Trim, which is a layer-wise convex scheme to prune a pre-trained deep neural network. Deep learning has become a method of choice for many AI applications, ranging from image recognition to language translation. Thanks to algorithmic and computational advances, we are now able to train bigger and deeper neural networks resulting in increased AI accuracy. However, because of increased power consumption and memory usage, it is impractical to deploy such models on embedded devices with limited hardware resources and power constraints. One practical way to overcome this challenge is to reduce the model complexity without sacrificing accuracy. The solution involves removing potentially redundant weights to make the network sparser.