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
Year: 2017
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
Learning to learn by gradient descent by gradient descent
Learning to learn by gradient descent by gradient descent Andrychowicz et al. NIPS 2016 One of the things that strikes me when I read these NIPS papers is just how short some of them are - between the introduction and the evaluation sections you might find only one or two pages! A general form is … Continue reading Learning to learn by gradient descent by gradient descent
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
Welcome to 2017
A big thank you to those of you who have been following the blog for some time now, and welcome to all of you joining for the first time in 2017! I spent the holiday break fine-tuning my writing and publishing process. The biggest difference regular readers will notice is that I've figured out a … Continue reading Welcome to 2017
the morning paper 