Ruslan Salakhutdinov

TL;DR: This work shows how to use unlabeled data and a deep belief net (DBN) to learn a good covariance kernel for a Gaussian process.

Abstract: We propose a novel extension of the encoder-decoder framework, called a review network. The review network is generic and can enhance any existing encoder- decoder model: in this paper, we consider RNN decoders with both CNN and RNN encoders. The review network performs a number of review steps with attention mechanism on the encoder hidden states, and outputs a thought vector after each review step; the thought vectors are used as the input of the attention mechanism in the decoder. We show that conventional encoder-decoders are a special case of our framework. Empirically, we show that our framework improves over state-of- the-art encoder-decoder systems on the tasks of image captioning and source code captioning.

TL;DR: This work proposes a method for improving classification performance for high capacity classifiers by discovering similar classes and transferring knowledge among them, which learns to organize the classes into a tree hierarchy, and proposes an algorithm for learning the underlying tree structure.

TL;DR: In this paper, a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image is proposed, which is end-to-end trainable, deterministic and problem-agnostic.

TL;DR: ActorMimic as discussed by the authors exploits the use of deep reinforcement learning and model compression techniques to train a single policy network that learns how to act in a set of distinct tasks by using the guidance of several expert teachers.