Alireza Makhzani

Learn More
In this paper, we propose the “adversarial autoencoder” (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior of the hidden code vector of the autoencoder with an arbitrary prior distribution. Matching the aggregated posterior to(More)
In this paper, we propose a winner-take-all method for learning hierarchical sparse representations in an unsupervised fashion. We first introduce fully-connected winner-take-all autoencoders which use mini-batch statistics to directly enforce a lifetime sparsity in the activations of the hidden units. We then propose the convolutional winner-take-all(More)
Recently, it has been observed that when representations are learnt in a way that encourages sparsity, improved performance is obtained on classification tasks. These methods involve combinations of activation functions, sampling steps and different kinds of penalties. To investigate the effectiveness of sparsity by itself, we propose the “k sparse(More)
There is a recent interest in developing algorithms for the reconstruction of jointly sparse signals, which arises in a large number of applications. In this work, we study the problem of wide-band spectrum sensing for cognitive radio networks using compressed sensing to exploit the underlying joint sparsity structure in a distributed setting. In(More)
In this paper, we define a new Joint Sparsity Model (JSM) and use Principal Component Analysis followed by Minimum Description Length and Compressive Sensing to reconstruct spatially and temporally correlated signals in a sensor network. The proposed model decomposes each sparse signal into two sparse components. The first component has a common support(More)
This paper introduces SC2LE (StarCraft II Learning Environment), a reinforcement learning environment based on the game StarCraft II. This domain poses a new grand challenge for reinforcement learning, representing a more difficult class of problems than considered in most prior work. It is a multi-agent problem with multiple players interacting; there is(More)
In this paper, we describe the “PixelGAN autoencoder”, a generative autoencoder in which the generative path is a convolutional autoregressive neural network on pixels (PixelCNN) that is conditioned on a latent code, and the recognition path uses a generative adversarial network (GAN) to impose a prior distribution on the latent code. We show that different(More)
  • 1