• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables

    WHY? Reparameterization trick is a useful technique for estimating gradient for loss function with stochastic variables. While score function extimators suffer from great variance, RT enable the gradient to be estimated with pathwise derivatives. Even though reparameterization trick can be applied to various kinds of random variables enabling backpropagation, it...


  • How Does Batch Normalization Help Optimization? (No, It Is Not About Internal Covariate Shift

    WHY? While the effect of batch normalization was widely proven empirically, the exact mechanism of it is yet been understood. Commonly known explanation for this was internal covariance shift(ICS) meaning the change in the distribution of layer inputs caused by updates to the preceeding layers. WHAT? Critic So? Ha, David,...


  • World Models

    WHY? Instead of instantly responding to incoming stimulus, having a model of environment to make some level of prediction would help perform in reinforcement learning. WHAT? Agent model of this paper consists of three parts: Vision(V), Memory(M), and Controller(C). Since simulating the whole pixels of environment is inefficient, VAE model...


  • Gradient Estimation Using Stochastic Computation Graphs

    WHY? Many machine learning problems involves loss function that contains random variables. To perform backpropagation, estimating gradient of the loss function is required. WHAT? This paper tried to formalize the computation of gradient of loss function with computation graphs. Assume we want to compute . There are two differnt way...


  • Amortized Inference in Probabilistic Reasoning

    WHY? Former studies on probabilistic reasoning assume that reasoning is memoryless, which means all the inference occur independently without the reuse of previous computation. WHAT? This paper tried to prove that probabilistic reasoning process of human is a amortized inference. When some queries are parts of complex queries, brain memorize...