http://openaccess.thecvf.com/content_cvpr_2017/papers/Jie_Deep_Self-Taught_Learning_CVPR_2017_paper.pdf Deep Self-Taught Learning for Weakly ...
Active Object Localization with Deep Reinforcement Learning ICCV 最近Deep Reinforcement Learning算是火了一把,在Google Deep Mind的主頁上,更是許多關於此的paper,基本都發在ICML,AAAI,IJCAI等各種人工智能,機器學習的牛會頂刊,甚至是Nature,可以參考其官方publica ...
2016-04-27 13:16 10 4090 推薦指數:
http://openaccess.thecvf.com/content_cvpr_2017/papers/Jie_Deep_Self-Taught_Learning_CVPR_2017_paper.pdf Deep Self-Taught Learning for Weakly ...
Deep Reinforcement Learning with Double Q-learning Google DeepMind Abstract 主流的 Q-learning 算法過高的估計在特定條件下的動作值。實際上,之前是不知道是否這樣的過高估計是 common ...
Dueling Network Architectures for Deep Reinforcement Learning ICML 2016 Best Paper 摘要:本文的貢獻點主要是在 DQN 網絡結構上,將卷積神經網絡提出的特征,分為兩路走,即:the state ...
Playing Atari with Deep Reinforcement Learning 《Computer Science》, 2013 Abstract: 本文提出了一種深度學習方法,利用強化學習的方法,直接從高維的感知輸入中學習控制策略。模型是一個卷積神經網絡 ...
Asynchronous Methods for Deep Reinforcement Learning ICML 2016 深度強化學習最近被人發現貌似不太穩定,有人提出很多改善的方法,這些方法有很多共同的 idea:一個 online 的 agent 碰到的觀察到的數據 ...
Is object localization for free? –Weakly-supervised learning with convolutional neural networks. Maxime Oquab, Leon Bottou, Ivan Laptev, Josef ...
Hierarchical Object Detection with Deep Reinforcement Learning NIPS 2016 WorkShop Paper : https://arxiv.org/pdf/1611.03718v1.pdf ...
的識別效果。 這篇論文的主要思想是通過學習兩個deep network來構建face attrib ...