papers | Deep Learning JP - Part 75

Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm

Deep Reinforcement Learning that Matters

Population Based Training of Neural Networks

Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

Backpropagation through the Void: Optimizing control variates for black-box gradient estimation

Rainbow: Combining Improvements in Deep Reinforcement Learning

Controllable Invariance through Adversarial Feature Learning

Deep Direct Reinforcement Learning for Financial Signal Representation and Trading

Learning to Act by Predicting the Future

A Bayesian Perspective on Generalization and Stochastic Gradient Descent

75 / 94« 先頭 «...10 20 30...73 747576 77...80 90...»最後 »