Perl 6 - the future is here, just unevenly distributed

IRC log for #marpa, 2016-02-03

| Channels | #marpa index | Today | | Search | Google Search | Plain-Text | summary

All times shown according to UTC.

Time Nick Message
05:20 VsyachePuz small AI U.K. startup called DeepMind, acquireg by google in 2014. Computer win Go champion 5 times in row. Game "Go" is far more challenging for computers than, say, chess for two reasons: the number of potential moves each turn is far higher, and there is no simple way to measure material advantage. A player must therefore learn to recognize abstract patterns in hundreds of pieces placed across the board. Deep learning
05:20 VsyachePuz involves training a large simulated neural network to respond to patterns in data. http://www.nature.com/nature/journa​l/v529/n7587/full/nature16961.html
05:24 VsyachePuz Published online 27 January 2016
05:27 VsyachePuz AlphaGo essentially taught itself how to win. “The same technique can be used to achieve extremely high performance on many other games as well,”
05:31 VsyachePuz The technical idea of reinforcement learning - getting computers to learn to improve their behaviour to achieve goals. This is certainly a major breakthrough for AI, with wider implications.
11:57 maybekoo joined #marpa
13:19 kaare__ joined #marpa
17:18 maybekoo5 joined #marpa
23:48 Idiosyncrat joined #marpa

| Channels | #marpa index | Today | | Search | Google Search | Plain-Text | summary