Aligning superhuman AI with human behavior: chess as a model system, McIlroy-Young et al., KDD’20 t’s been a while, but it’s time to start reading CS papers again! We’ll ease back into it with one or two papers a week for a few weeks, building back up to something like 3 papers a week at … Continue reading Aligning superhuman AI with human behaviour: chess as a model systems
Category: Machine Learning
The machine learning subset of AI. Includes deep learning among other topics.
Learning to act by predicting the future
Learning to act by predicting the future Dosovitskiy & Koltun, ICLR'17 The Direct Future Prediction (DFP) model won the 'Full Deathmatch' track of the Visual Doom AI Competion in 2016. The competition pits agents against each other, with their performance measured by how many 'frags' they get. (A frag is a kill, apparently - not … Continue reading Learning to act by predicting the future
Neural architecture search with reinforcement learning
Neural architecture search with reinforcement learning Zoph & Le, ICLR'17 Earlier this year we looked at 'Large scale evolution of image classifiers' which used an evolutionary algorithm to guide a search for the best network architectures. In today's paper, Zoph & Le also demonstrate that learning network architectures (and also in their case recurrent cell … Continue reading Neural architecture search with reinforcement learning
Semi-supervised knowledge transfer for deep learning from private training data
Semi-supervised knowledge transfer for deep learning from private training data Papernot et al., ICLR'17 How can you build deep learning models that are trained on sensitive data (e.g., concerning individuals), and be confident to deploy those models in the wild knowing that they won't leak any information about the individuals in the training set? As … Continue reading Semi-supervised knowledge transfer for deep learning from private training data
End-to-end optimized image compression
End-to-end optimized image compression Ballé et al., ICLR'17 We'll be looking at some of the papers from ICLR'17 this week, starting with "End-to-end optimized image compression" which makes a nice comparison with the Dropbox JPEG compression paper that we started with last week. Of course you won't be surprised to find out that the authors … Continue reading End-to-end optimized image compression
Large-scale evolution of image classifiers
Large-scale evolution of image classifiers Real et al., 2017 I'm sure you noticed the bewildering array of network architectures in use when we looked at some of the top convolution neural network papers of the last few years last week (Part 1, Part2, Part 3). With sufficient training data, these networks can achieve amazing feats, … Continue reading Large-scale evolution of image classifiers
A miscellany of fun deep learning papers
To round out the week, I thought I'd take a selection of fun papers from the 'More papers from 2016' section of top 100 awesome deep learning papers list. Colorful image colorization, Zhang et al., 2016 Texture networks: feed-forward synthesis of textures and stylized images Generative visual manipulation on the natural image manifold, Zhu et … Continue reading A miscellany of fun deep learning papers
Recurrent Neural Network models
Today we're pressing on with the top 100 awesome deep learning papers list, and the section on recurrent neural networks (RNNs). This contains only four papers (joy!), and even better we've covered two of them previously (Neural Turing Machines and Memory Networks, the links below are to the write-ups). That leaves up with only two … Continue reading Recurrent Neural Network models
Convolution neural networks, Part 3
Today we're looking at the final four papers from the 'convolutional neural networks' section of the 'top 100 awesome deep learning papers' list. Deep residual learning for image recognition, He et al., 2016 Identity mappings in deep residual networks, He et al., 2016 Inception-v4, inception-resnet and the impact of residual connections or learning, Szegedy et … Continue reading Convolution neural networks, Part 3
Convolution neural nets, Part 2
Today it's the second tranche of papers from the convolutional neural nets section of the 'top 100 awesome deep learning papers' list: Return of the devil in the details: delving deep into convolutional nets, Chatfield et al., 2014 Spatial pyramid pooling in deep convolutional networks for visual recognition, He et al., 2014 Very deep convolutional … Continue reading Convolution neural nets, Part 2
the morning paper 