Researchers at the University of California, Irvine have created an artificial intelligence system that can solve a Rubik’s Cube in an average of 1.2 seconds, in about 20 moves. That is two seconds faster than the current human world record of 3.47 seconds, while people who can finish the puzzle quickly usually do so in about 50.
Engadged reported that this artificial intelligence – DeepCubeA – does not hold the record for automated Rubik’s Cube solving because last year, scientists built another machine which is capable of solving the famous Hungarian invention in 0.38 second. Massachusetts Institute of Technology’s min2phase algorithm, which is not an AI system, solved it three times faster than DeepCubeA. While other methods were specifically designed to solve the cube, DeepCubeA had to forge its own path.
However, creators of DeepCubeA still have not figured out how the AI was able to recognise that the cube has six blocks of colours on each side of it and billions of combinations to solve the cube. After the researchers showed the AI what the result would look like when the cube is completed, the system was able to figure out on its own how to get there, which is still a big mystery for scientists.
The researchers started with a simulated version of a completed Rubik’s Cube, then mixed it. DeepCubeA then trained itself to solve the puzzle over two days, improving its skill as it attempted increasingly difficult combinations.
Researchers gave DeepCubeA 10 billion combinations and urged it to solve the puzzles in 30 or fewer moves. The AI was then put to the test on a thousand combinations. It cracked the puzzle every time and did so in the minimum number of moves in around 60 per cent of attempts.
This brilliant AI system uses a neural network – similar to how humans process information – with machine learning techniques in which an AI system learns by detecting patterns and theorising with little human input. It adopts a reinforcement learning approach, by which it learned “how to solve increasingly difficult states in reverse from the goal state without any specific domain knowledge.”
For another awesome video CLICK HERE
Featured image: Youtube