Chapter 5. Compressing and Regularizing Deep Neural Networks
Deep neural networks have evolved to be the state-of-the-art technique for machine learning tasks ranging from computer vision and speech recognition to natural language processing. However, deep learning algorithms are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources.
To address this limitation, deep compression significantly reduces the computation and storage required by neural networks. For example, for a convolutional neural network with fully connected layers, such as Alexnet and VGGnet, it can reduce the model size by 35×-49×. Even for fully convolutional neural networks such as GoogleNet and SqueezeNet, deep compression can still reduce the model size by 10x. Both scenarios results in no loss of prediction accuracy.
Current Training Methods Are Inadequate
Compression without losing accuracy means there’s significant redundancy in the trained model, which shows the inadequacy of current training methods. To address this, I’ve worked with Jeff Pool of NVIDIA, Sharan Narang of Baidu, and Peter Vajda of Facebook to develop the dense-sparse-dense (DSD) training, a novel training method that first regularizes the model through sparsity-constrained optimization, and improves the prediction accuracy by recovering and retraining on pruned weights. At test time, the final model produced by DSD training still has the same architecture ...