Apr 22, 2016

Related: https://www.newscientist.com/article/2076552-google-deepmind...

Google DeepMind AI navigates a Doom-like 3D maze just by looking

Paper: http://arxiv.org/abs/1602.01783

Apr 13, 2016

The progress in machine learning/deep learning for last 5 years has been literally staggering. Read about new state of art results. There is already superhuman visual object recognition, voice recognition, good machine translation, description of scenes in natural language, question answering (facebook babi dataset), visual question answering, algorithm learning (neural turing machines, neural GPUs), and finally really strong reinforcement learning (deepmind's DQN, A3C algorithms).

The last one, reinforcement learning, is really important because it's a basis for general intelligence. By rewarding/punishing a reinforcement learning agent you can train it to execute very complex tasks, for example navigating a maze with pixel input or controlling a robot body to do some tasks. DeepMind is on the cutting edge of this kind of research, you can read about their latest agent here http://arxiv.org/abs/1602.01783

With such rate of progress it's not inconceivable if a sub-human but general intelligence could be developed in 10-20 years, or even sooner.

Mar 09, 2016

see also by the same team:


Feb 06, 2016

Link to paper: http://arxiv.org/abs/1602.01783