• Publications
  • Influence
Adam: A Method for Stochastic Optimization
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Expand
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
An attention based model that automatically learns to describe the content of images is introduced that can be trained in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound. Expand
Layer Normalization
Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique calledExpand
Do Deep Nets Really Need to be Deep?
This paper empirically demonstrate that shallow feed-forward nets can learn the complex functions previously learned by deep nets and achieve accuracies previously only achievable with deep models. Expand
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
This work proposes to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature with trust region, which is the first scalable trust region natural gradient method for actor-critic methods. Expand
Dream to Control: Learning Behaviors by Latent Imagination
Dreamer is presented, a reinforcement learning agent that solves long-horizon tasks purely by latent imagination and efficiently learn behaviors by backpropagating analytic gradients of learned state values through trajectories imagined in the compact state space of a learned world model. Expand
Lookahead Optimizer: k steps forward, 1 step back
Lookahead improves the learning stability and lowers the variance of its inner optimizer with negligible computation and memory cost, and can significantly improve the performance of SGD and Adam, even with their default hyperparameter settings. Expand
Multiple Object Recognition with Visual Attention
The model is a deep recurrent neural network trained with reinforcement learning to attend to the most relevant regions of the input image and it is shown that the model learns to both localize and recognize multiple objects despite being given only class labels during training. Expand
Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
This work defines a novel method of multitask and transfer learning that enables an autonomous agent to learn how to behave in multiple tasks simultaneously, and then generalize its knowledge to new domains, and uses Atari games as a testing environment to demonstrate these methods. Expand
Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions
A new model is presented that can classify unseen categories from their textual description and takes advantage of the architecture of CNNs and learn features at different layers, rather than just learning an embedding space for both modalities, as is common with existing approaches. Expand