Journal ArticleDOI
Mastering the game of Go with deep neural networks and tree search
David Silver,Aja Huang,Chris J. Maddison,Arthur Guez,Laurent Sifre,George van den Driessche,Julian Schrittwieser,Ioannis Antonoglou,Veda Panneershelvam,Marc Lanctot,Sander Dieleman,Dominik Grewe,John Nham,Nal Kalchbrenner,Ilya Sutskever,Timothy P. Lillicrap,Madeleine Leach,Koray Kavukcuoglu,Thore Graepel,Demis Hassabis +19 more
TLDR
Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go.Abstract:
The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of stateof-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.read more
Citations
More filters
Journal ArticleDOI
Dermatologist-level classification of skin cancer with deep neural networks
Andre Esteva,Brett Kuprel,Roberto A. Novoa,Justin M. Ko,Susan M. Swetter,Susan M. Swetter,Helen M. Blau,Sebastian Thrun +7 more
TL;DR: This work demonstrates an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists, trained end-to-end from images directly, using only pixels and disease labels as inputs.
Journal ArticleDOI
Mastering the game of Go without human knowledge
David Silver,Julian Schrittwieser,Karen Simonyan,Ioannis Antonoglou,Aja Huang,Arthur Guez,Thomas Hubert,Lucas Baker,Matthew Lai,Adrian Bolton,Yutian Chen,Timothy P. Lillicrap,Fan Hui,Laurent Sifre,George van den Driessche,Thore Graepel,Demis Hassabis +16 more
TL;DR: An algorithm based solely on reinforcement learning is introduced, without human data, guidance or domain knowledge beyond game rules, that achieves superhuman performance, winning 100–0 against the previously published, champion-defeating AlphaGo.
Proceedings ArticleDOI
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Ramprasaath R. Selvaraju,Michael Cogswell,Abhishek Das,Ramakrishna Vedantam,Devi Parikh,Dhruv Batra +5 more
TL;DR: This work combines existing fine-grained visualizations to create a high-resolution class-discriminative visualization, Guided Grad-CAM, and applies it to image classification, image captioning, and visual question answering (VQA) models, including ResNet-based architectures.
Proceedings ArticleDOI
Towards Evaluating the Robustness of Neural Networks
Nicholas Carlini,David Wagner +1 more
TL;DR: In this paper, the authors demonstrate that defensive distillation does not significantly increase the robustness of neural networks by introducing three new attack algorithms that are successful on both distilled and undistilled neural networks with 100% probability.
Journal ArticleDOI
Places: A 10 Million Image Database for Scene Recognition
TL;DR: The Places Database is described, a repository of 10 million scene photographs, labeled with scene semantic categories, comprising a large and diverse list of the types of environments encountered in the world, using the state-of-the-art Convolutional Neural Networks as baselines, that significantly outperform the previous approaches.
References
More filters
Book ChapterDOI
A lock-free multithreaded monte-carlo tree search algorithm
Markus Enzenberger,Martin Müller +1 more
TL;DR: A new lock-free parallel algorithm for Monte-Carlo tree search which takes advantage of the memory model of the IA-32 and Intel-64 CPU architectures and intentionally ignores rare faulty updates of node values is presented.
Book ChapterDOI
Monte-Carlo simulation balancing in practice
TL;DR: The effectiveness of simulation balancing is demonstrated in a more realistic setting and a state-of-the-art program, Erica, learned an improved playout policy on the 9×9 board, without requiring any external expert to provide position evaluations.
Proceedings Article
Bootstrapping from Game Tree Search
TL;DR: This paper introduces a new algorithm for updating the parameters of a heuristic evaluation function, by updating the heuristic towards the values computed by an alpha-beta search, and implemented this algorithm in a chess program Meep, using a linear heuristic function.
Book ChapterDOI
Evaluation in Go by a Neural Network Using Soft Segmentation
TL;DR: A neural network architecture is presented that is able to build a soft segmentation of a two-dimensional input that is applied to position evaluation in the game of Go.
Book ChapterDOI
On the scalability of parallel UCT
TL;DR: This paper first analyzes the single-threaded scaling of Fuego and finds that there is an upper bound on the play-quality improvements which can come from additional search, and determines the maximum amount of parallelism supported by MCTS.