1. Categorical reparameterization with gumbel-softmax;jang;ArXiv Preprint,2016
2. On calibration of modern neural networks;guo;International Conference on Machine Learning,2017
3. Determining the optimal temperature parameter for Softmax function in reinforcement learning
4. Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters;bridle;Advances in neural information processing systems,1989