You’d remember AlphaGo, the first AI program that defeated Lee Sedol, a world champion in the game of Go by 4 t0 1 right?, its “big brother”, an improved version, called AlphaGo Zero is the new kid on the block. It defeated its predecessor by a whooping 100 to 0.
Its creator believe that AlphaGo Zero is more powerful and is “arguably the strongest Go player in history”.
What are the difference between AlphaGo and AlphaGo Zero?
Unlike AlphaGo, which initially trained on thousands of human amateur and professional games to learn how to play Go, AlphaGo Zero skips this step and learns to play simply by playing games against itself, starting from completely random play. In doing so, it quickly surpassed human level of play and defeated the AlphaGo by 100 games to 0.
This feat was possible by using what is called a “reinforcement learning”, in which AlphaGo Zero becomes its own teacher. The system starts off with a neural network that knows nothing about the game of Go. It then plays games against itself, by combining this neural network with a powerful search algorithm. As it plays, the neural network is tuned and updated to predict moves, as well as the eventual winner of the games.
Notable Difference Between AlphaGo and AlphaGo Zero includes;
- AlphaGo Zero only uses the black and white stones from the Go board as its input, whereas previous versions of AlphaGo included a small number of hand-engineered features.
- It uses one neural network rather than two. Earlier versions of AlphaGo used a “policy network” to select the next move to play and a ”value network” to predict the winner of the game from each position. These are combined in AlphaGo Zero, allowing it to be trained and evaluated more efficiently.
- AlphaGo Zero does not use “rollouts” – fast, random games used by other Go programs to predict which player will win from the current board position. Instead, it relies on its high quality neural networks to evaluate positions.
It actually took AlphaGo Zero just three days of self-play training to emphatically defeat AlphaGo. All of these differences help improve the performance of the system and make it more general. But it is the algorithmic change that makes the system much more powerful and efficient.
Creators of AlphaGo and AlphaGo Zero, DeepMind believed that, these acheivements of creativity is a confidence that AI will be a multiplier for human ingenuity, helping their mission to solve some of the most important challenges humanity is facing. If similar techniques can be applied to other structured problems, such as protein folding, reducing energy consumption or searching for revolutionary new materials, the resulting breakthroughs have the potential to positively impact society.
Artificial intelligence is the science and engineering of making intelligent machines or developing intelligent behaviour by machines.
In computer science, Artificial Intelligence is defined as the study of intelligent agents, that is, any device that perceives its environment and takes actions that maximize its chance of success at some goal. It can also be said to be a way of making a computer, a computer-controlled robot, or a software think intelligently, in the similar manner the intelligent humans think.
This branch of computer science was made popular by The Turing test, developed by Alan Turing in 1950, is a test of a machine’s ability to exhibit intelligent behaviour equivalent to, or indistinguishable from, that of a human.
The Turing test proposed that a human evaluator would judge natural language conversations between a human and a machine designed to generate human-like responses. The evaluator would be aware that one of the two partners in conversation is a machine, and all participants would be separated from one another. The conversation would be limited to a text-only channel such as a computer keyboard and screen so the result would not depend on the machine’s ability to render words as speech. If the evaluator cannot reliably tell the machine from the human, the machine is said to have passed the test.