Microsoft invests $1 billion in OpenAI and becomes its cloud partner
In July 2019 Microsoft invested $1 billion in OpenAI and became its exclusive computing partner, with OpenAI's services to run on Microsoft Azure.
Total 183 · Clear filters
OpenAI Five beats Dota 2 world champions OG
On 13 April 2019, OpenAI Five — a team of reinforcement-learning bots — beat OG, the reigning Dota 2 world champions, in a best-of-three in San Francisco, and days later won 99.4% of games in a public online arena.
Google researchers publish BERT on arXiv
On 11 October 2018 Google researchers posted the BERT paper to arXiv. BERT uses context from both directions in every layer, and a single added output layer is enough to adapt it to tasks such as question answering.
OpenAI publishes the first GPT paper on generative pre-training
On 11 June 2018 OpenAI published a paper on generative pre-training: a language model first learns from unlabeled text and is then adapted to specific tasks. The approach improved the state of the art on 9 of the 12 tasks studied.
“Attention Is All You Need” is posted to arXiv, introducing the Transformer
On 12 June 2017 a team of researchers, most of them at Google, posted the paper Attention Is All You Need to arXiv. It introduced the Transformer, a neural network built only on attention, which became the basis for most later large language models.
Google reveals the Tensor Processing Unit
In May 2016 Google disclosed the Tensor Processing Unit, a custom chip built for machine learning that had already run in its data centers for over a year and powered RankBrain, Street View and AlphaGo.
DeepMind posts its deep Q-network Atari paper
On 19 December 2013, DeepMind researchers posted a paper showing that one convolutional network, trained with a variant of Q-learning, could learn Atari 2600 control policies directly from raw pixels and outperform prior methods on six of seven games.
Spirit and Opportunity land on Mars with autonomous navigation
In January 2004 NASA's Spirit and Opportunity landed on Mars carrying autonomous navigation software. The mission was planned around about one kilometre of driving; the rovers went much farther, with a large share of their early driving decided on Mars rather than on Earth.
Nomad autonomously searches for meteorites in Antarctica
In January 2000, Carnegie Mellon announced that its NASA-funded rover prototype Nomad was searching for meteorites in Antarctica, and that the public could follow the hunt through the Big Signal Web site. The BBC reported the expedition as the first time a robot found extraterrestrial material on Earth.
The first official RoboCup games and conference
The first official RoboCup games and conference, held in 1997 as planned with IJCAI-97 in Nagoya, drew more than 40 real and simulated teams and over 5,000 spectators, and marked the first step toward robotic soccer players that could beat a human World Cup champion team.
Pre-RoboCup-96, the first robot soccer competition
Held in Osaka in November 1996 alongside IROS-96, Pre-RoboCup-96 was the first robot soccer competition aimed at research and education, with eight simulation-league teams and a middle-size robot demonstration; official RoboCup games followed in 1997.
IJCAI-95 announces the first Robot World Cup games
At IJCAI-95 in Montreal in August 1995, organizers announced the first Robot World Cup, to be held with IJCAI-97 in Nagoya, and set up Pre-RoboCup-96 plus the Soccer Server simulator.
The Robot World Cup Initiative is launched
In June 1993, researchers including Minoru Asada, Yasuo Kuniyoshi and Hiroaki Kitano proposed a robot soccer competition tentatively called the Robot J-League. International interest soon led to its renaming as the Robot World Cup Initiative, or RoboCup.
Robot soccer is proposed as an AI grand challenge
In 1992, Alan Mackworth's paper on seeing robots and a Tokyo workshop on AI grand challenges independently put forward robot soccer as a way to drive AI and robotics research.
TD-Gammon developed at IBM
TD-Gammon was an IBM backgammon program built by Gerald Tesauro that taught itself to evaluate positions by playing against itself with temporal-difference learning, reaching a level just below top human players and becoming an early landmark for reinforcement learning.