- #1
Ackbach
Gold Member
MHB
- 4,155
- 89
You chess fans out there might find https://chess24.com/en/read/news/deepmind-s-alphazero-crushes-chess interesting. No domain-specific knowledge required!
greg1313 said:...which leads me to the question "Can we construct an algorithm that, given the rules of math, teaches itself math and consequently arrives at solutions for problems currently unattainable for humans". Maybe not in this era but I certainly don't know that.
Jameson said:I work with machine learning on a daily basis in my day job, so I've really become interested in these types of projects. Neural networks have become absolutely amazing with regards to the types of problems they can solve. Stockfish has been the gold standard of chess for years now and AlphaZero actually calculated less potential moves than Stockfish on average. Instead it will search for patterns that lead to optimal outcomes.
jonah said:Beer soaked doubt follows.
https://medium.com/@josecamachocoll...-a-scientific-breakthrough-in-ai-bf66ae1c84f2
AlphaZero Crushes Chess is an artificial intelligence program created by Google's DeepMind that has achieved groundbreaking success in the game of chess.
AlphaZero Crushes Chess uses a combination of deep neural networks and reinforcement learning techniques to teach itself how to play chess at an extremely high level.
Unlike traditional chess programs which rely heavily on human input and strategies, AlphaZero Crushes Chess learns from scratch and creates its own unique strategies based on reinforcement learning.
AlphaZero Crushes Chess has achieved unprecedented success, defeating the world champion chess program Stockfish by a score of 28 wins, 72 draws, and 0 losses in a 100-game match.
AlphaZero Crushes Chess has shown the potential for artificial intelligence to surpass human capabilities in complex tasks, and has opened the door for further advancements in AI and machine learning.