Googles Deep Mind Alpha Go Alpha Go Zero

Google’s - Deep. Mind Alpha. Go & Alpha. Go Zero Direct Quotes from: Demis Hassabi, & David Silver, October 2017, URL: https: //deepmind. com/blog/alphagozero-learning-scratch/

Google's Deep Mind Explained! - Self Learning A. I. • Source: https: //www. youtube. com/watch? v=Tn. UYc. Tu. ZJp. M

0 day

3 days

21 days

40 days

Reinforcement learning Direct quotes from: Wikipedia, 2017 • • • Reinforcement learning (RL) is an area of machine learning inspired by behaviourist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. … In machine learning, the environment is typically formulated as a Markov decision process (MDP), as many reinforcement learning algorithms for this context utilize dynamic programming techniques. [1] The main difference between the classical techniques and reinforcement learning algorithms is that the latter do not need knowledge about the MDP and they target large MDPs where exact methods become infeasible. Reinforcement learning differs from standard supervised learning in that correct input/output pairs are never presented, nor sub-optimal actions explicitly corrected. Instead the focus is on on-line performance Direct quotes from URL: https: //en. wikipedia. org/wiki/Reinforcement_learning

GPU-graphics processing unit

Tensor Processing Unit (TPU) Direct quotes from: Wikipedia, 2017 • • A tensor processing unit (TPU) is an application-specific integrated circuit (ASIC) developed by Google specifically for neural network machine learning. Compared to a graphics processing unit, it is designed for a high volume of low precision computation (e. g. as little as 8 -bit precision[1]) … The chip has been specifically designed for Google's Tensor. Flow framework. However, Google still uses CPUs and GPUs for other types of machine learning. [3] Google's TPUs are proprietary and are not commercially available. Google has stated that they were used in the Alpha. Go versus Lee Sedol series of man-machine Go games, [2] as well as in the Alpha. Zero system …. Google has also used TPUs for Google Street View text processing, and was able to find all the text in the Street View database in less than five days. In Google Photos, an individual TPU can process over 100 million photos a day. Direct quotes from URL: https: //en. wikipedia. org/wiki/Tensor_processing_unit

Google AI experiments • https: //experiments. withgoogle. com/collection/ai Source URL: https: //experiments. withgoogle. com/collection/ai