Discouraging Words from Machines Impair Human Game Play
A new CMU study shows that people who played a game with a humanoid robot known as Pepper performed worse when the robot discouraged them and better when it encouraged them. “This is one of the first studies of human-robot interaction in an environment where they are not cooperating,” said co-author Fei Fang, an assistant professor in the Institute for Software Research.
(Carnegie Mellon University)
Bot Can Beat Humans in Multiplayer Hidden-Role Games
MIT researchers have developed a bot, DeepRole, equipped with artificial intelligence that can beat human players in tricky online multiplayer games where player roles and motives are kept secret. At the Conference on Neural Information Processing Systems next month, the researchers will present DeepRole.
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
In this work, researchers present the MuZero algorithm which, by combining a tree-based search with a learned model, achieves superhuman performance in a range of challenging and visually complex domains, without any knowledge of their underlying dynamics.
(DeepMind & University College London)
The Deep Learning Revolution and Its Implications for Computer Architecture and Chip Design
This paper is a companion paper to a keynote talk at the 2020 International Solid-State Circuits Conference (ISSCC) discussing some of the advances in machine learning, and their implications on the kinds of computational devices we need to build, especially in the post-Moore’s Law-era.
Benchmarking Safe Exploration in Deep Reinforcement Learning
OpenAI has released Safety Gym, a suite of environments and tools for measuring progress towards reinforcement learning agents that respect safety constraints while training. They also provide a standardized method of comparing algorithms and how well they avoid costly mistakes while learning.
(OpenAI) / (OpenAI Blog)
RandAugment: Practical Automated Data Augmentation with A Reduced Search Space
RandAugment has a significantly reduced search space which allows it to be trained on the target task with no need for a separate proxy task. Furthermore, due to the parameterization, the regularization strength may be tailored to different model and dataset sizes.
You May Also Like
Google Brain’s Hugo Larochelle on Few-Shot Learning
“Few-shot learning is the problem of learning new tasks from little amounts of labeled data. This topic has gained tremendous interest in the past few years, with several new methods being proposed each month,” Google Brain Group in Montréal Lead Hugo Larochelle said in his keynote at the recent RE•WORK Deep Learning Summit in Montréal.
Huawei Tops ETH Zurich 2019 Smartphone Deep Learning Rankings
Huawei took 6 of the top 10 spots for AI-ready smartphones, with the Mate 30 Pro 5G and Mate 30 Pro nearly doubling the scores of other top 10 finishers. “Right now, Huawei devices with the Kirin 990 5G SoC can run floating-point neural networks up to four times faster than phones with other chipsets, thus they are getting a significantly higher total AI score,” Ignatov said.
Global AI Events
December 2-6: AWS re:Invent 2019 in Las Vegas, United States
December 8-14: 2019 Conference on Neural Information Processing Systems (NeurIPS 2019) in Vancouver, Canada
January 7-10: CES 2020 in Las Vegas, United States
February 7-12: AAAI 2020 in New York, United States