[Survey]Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1DeepLearning Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio BinaryNetは、weightとactivationを2値化したhardware friendlyなDNN(Deep Neural Network)です。 論文