读书会总体介绍 & DeepMind‘s DQN for playing Atari games
发表于 2015-04-08 05:08:37 由 king

第一次活动:读书会总体介绍 & DeepMind‘s DQN for playing Atari games

时间:2015-4-19下午3点
地点:蕴味儿咖啡
  
主讲人:肖达,博士毕业于清华大学计算机系,现为北京邮电大学计算机学院讲师,彩云天气联合创始人。
  
  内容:
  1. 读书会介绍,参与者自我介绍,讨论商定后续活动的内容安排和主讲人分工
  2. 介绍并讨论DeepMind的深度强化学习网络用来打Atari游戏的工作
  
  
  读书会介绍和提纲
  题目:高级认知相关的另类深度学习
  2009年以来,深度学习在涉及到视觉、听觉等人类和哺乳动物共有的较低级认知功能的任务中取得突破性进展(如图像识别、语音识别)。在以 DNN和CNN为代表的主流深度学习之外,始于上世纪90年代的一些”另类“研究显示,在涉及到注意、长/短时记忆、语言、策略学习等人类特有的高级认知 功能的任务,深度学习(主要是具有各种特定结构的深度神经网络)也有巨大潜力尚待开发,并从2014年开始得到学术界越来越多的重视。本次读书会从中选取 若干有代表性的工作,分几个专题进行研读讨论,这些研究为深度学习(更一般地,大数据驱动的复杂模型学习)的下一步发展指出了方向。
  规模:6~7次,核心成员10人以内
  
  专题安排:
  Reinforcement learning & game playing
  Mnih, V., Kavukcuoglu, K., Silver, D., et al. Playing Atari with deep reinforcement learning. NIPS Deep Learning Workshop, 2013.
  Mnih, V., Kavukcuoglu, K., Silver, D., et al. Human-level control through deep reinforcement learning. Nature 518, 529–533, 2015.
  demo
  http://cs.stanford.edu/people/karpathy/convnetjs/demo/rldemo.html
  Guo, X., Singh, S., Lee, H., et al. Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning. NIPS 2014.
  Chris J. Maddison, Aja Huang, Ilya Sutskever, David Silver. Move Evaluation in Go Using Deep Convolutional Neural Networks. arXiv:1412.6564, 2014.
  Bakker, B. Reinforcement learning with Long Short-Term Memory. NIPS 2002.
  Koutnik J., Cuccu G., Schmidhuber J., Gomez F. Evolving Large-Scale Neural Networks for Vision-Based Reinforcement Learning. In Proc. Genetic and Evolutionary Computation Conference (GECCO), 2013.
  
  RNN / LSTM & sequence learning
  Hochreiter, S. and Schmidhuber, J. Long Short-Term Memory. Neural Computation, 9(8):1735–1780. 1997.
  Gers, A. and Schmidhuber, J. LSTM Recurrent Networks Learn Simple Context Free and Context Sensitive Languages. IEEE Transactions on Neural Networks 12(6):1333-1340, 2001.
  Sutskever, Ilya, Vinyals, Oriol, and Le, Quoc. Sequence to sequence learning with neural networks. NIPS 2014.
  Vinyals, Oriol, Toshev, Alexander, Bengio, Samy, and Erhan, Dumitru. Show and tell: A neural image caption generator. arXiv:1411.4555, November 2014.
  
  Attention
  Mnih, V., Heess, N., Graves, A., et al. Recurrent models of visual attention. NIPS 2014.
  Ba, Jimmy, Mnih, Volodymyr, and Kavukcuoglu, Koray. Multiple object recognition with visual attention. arXiv preprint arXiv:1412.7755, 2014.
  Bahdanau, Dzmitry, Cho, Kyunghyun, and Bengio, Yoshua. Neural machine translation by jointly learning to align and translate. arXiv:1409.0473, September 2014.
  Gregor, K., Danihelka, I., Graves, A., Wierstra, D. DRAW: A Recurrent Neural Network For Image Generation arXiv:1502.04623, 2015.
  
  Program learning, long-term memory and metalearning (learning to learn)
  Weston, Jason, Chopra, Sumit, and Bordes, Antoine. Memory networks. arXiv:1410.3916, 2014.
  Graves, Alex, Wayne, Greg, and Danihelka, Ivo. Neural turing machines. arXiv:1410.5401, 2014.
  Schmidhuber, J. An introspective network that can learn to run its own weight change algorithm. ICANN 1993.
  Hochreiter, S., Younger, A. S., Conwell, P. R. Learning to Learn Using Gradient Descent. ICANN 2001.
 

2012-2022 www.swarma.org, all rights reserved