Strategic attentive writer for learning macro-actions Vezhnevets et al. (Google DeepMind), NIPS 2016 Baldrick may have a cunning plan, but most Deep Q Networks (DQNs) just react to what's immediately in front of them and what has come before. That is, at any given time step they propose the best action to take there and … Continue reading Strategic attentive writer for learning macro-actions
Tag: Deep Learning
The deep learning subset of machine learning.
Unsupervised learning of 3D structure from images
Unsupervised learning of 3D structure from images Unsupervised learning of 3D structure from images Rezende et al. (Google DeepMind) NIPS,2016 Earlier this week we looked at how deep nets can learn intuitive physics given an input of objects and the relations between them. If only there was some way to look at a 2D scene … Continue reading Unsupervised learning of 3D structure from images
Matching networks for one shot learning
Matching networks for one shot learning Vinyals et al. (Google DeepMind), NIPS 2016 Yesterday we saw a neural network that can learn basic Newtonian physics. On reflection that's not totally surprising since we know that deep networks are very good at learning functions of the kind that describe our natural world. Alongside an intuitive understanding … Continue reading Matching networks for one shot learning
Interaction networks for learning about objects, relations and physics
Interaction networks for learning about objects, relations and physics Google DeepMind, NIPS 2016 Welcome back! There were so many great papers from OSDI '16 to cover at the end of last year that I didn't have a chance to get to NIPS. I'm kicking off this year therefore with a few of the Google DeepMind … Continue reading Interaction networks for learning about objects, relations and physics
TensorFlow: A system for large-scale machine learning
TensorFlow: A system for large-scale machine learning Abadi et al. (Google Brain) OSDI 2016 This is my last paper review for 2016! The Morning Paper will be taking a two week break for the holidays, resuming again on the 2nd January. Sometime inbetween I’ll do a short retrospective on the year. It seems fitting to … Continue reading TensorFlow: A system for large-scale machine learning
Playing FPS games with deep reinforcement learning
Playing FPS games with deep reinforcement learning Lample et al. arXiv preprint, 2016 When I wrote up ‘Asynchronous methods for deep learning’ last month, I made a throwaway remark that after Go the next challenge for deep learning systems would be to win an esports competition against the best human teams. Can you imagine the … Continue reading Playing FPS games with deep reinforcement learning
Achieving human parity in conversational speech recognition
Achieving Human Parity in Conversational Speech Recognition Xiong et al. Microsoft Technical Report, 2016 The headline story here is that for the first time a system has been developed that exceeds human performance in one of the most difficult of all human speech recognition tasks: natural conversations held over the telephone. This is known as … Continue reading Achieving human parity in conversational speech recognition
Towards deep symbolic reinforcement learning
Towards deep symbolic reinforcement learning Garnelo et al, 2016 Every now and then I read a paper that makes a really strong connection with me, one where I can't stop thinking about the implications and I can't wait to share it with all of you. For me, this is one such paper. In the great … Continue reading Towards deep symbolic reinforcement learning
Progressive neural networks
Progressive neural networks Rusu et al, 2016 If you've seen one Atari game you've seen them all, or at least once you've seen enough of them anyway. When we (humans) learn, we don't start from scratch with every new task or experience, instead we're able to build on what we already know. And not just … Continue reading Progressive neural networks
Asynchronous methods for deep reinforcement learning
Asynchronous methods for deep reinforcement learning Mnih et al. ICML 2016 You know something interesting is going on when you see a scalability plot that looks like this: That’s a superlinear speedup as we increase the number of threads, giving a 24x performance improvement with 16 threads as compared to a single thread. The result … Continue reading Asynchronous methods for deep reinforcement learning
the morning paper 