BinaryConnect: Training Deep Neural Networks with binary weights during propagations
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 28 (NIPS 2015), pp. 3123-3131, 2015.
Deep Neural Networks (DNN) have achieved state-of-the-art results in a wide range of tasks, with the best results obtained with large training sets and large models. In the past, GPUs enabled these breakthroughs because of their greater computational speed. In the future, faster computation at both training and test time is likely to be c...More
PPT (Upload PPT)