JUL 23, 2019 10:00 PM PDT

'Deep Learning Algorithm' Triumphs Over Human Thinking

WRITTEN BY: Nouran Amin

Solving the Rubik’s Cube has challenged human thinking since its inception in 1974. Now, the 3D logic puzzle is posed as an easy game for future artificial intelligence systems. Specifically, researchers at the University of California-Irvine have developed ‘DeepCubeA’—which is a deep reinforcement learning algorithm that aims to solve the Rubik’s cube in a fraction of a second without prior knowledge or in-game coaching.

Learn more on the history of the Rubik’s cube:

“Artificial intelligence can defeat the world’s best human chess and Go players, but some of the more difficult puzzles, such as the Rubik’s Cube, had not been solved by computers, so we thought they were open for AI approaches,” said senior author Pierre Baldi, UCI Distinguished Professor of computer science. “The solution to the Rubik’s Cube involves more symbolic, mathematical and abstract thinking, so a deep learning machine that can crack such a puzzle is getting closer to becoming a system that can think, reason, plan and make decisions.”

The study was published in Nature Machine Intelligence and describes how DeepCubeA can solve 100 percent of all test configurations of the Rubik’s cube along with successfully solving other combinatorial games—like the sliding tile puzzle, Lights Out and Sokoban.

A computer simulation of a completed Rubik’s cube puzzle was started to train DeepCubeA in isolation for two days with increasingly difficult series of combinations to complete

“It learned on its own,” Baldi noted, “our AI takes about 20 moves, most of the time solving it in the minimum number of steps. Right there, you can see the strategy is different, so my best guess is that the AI’s form of reasoning is completely different from a human’s.”

University of California-Irvine: The fastest people need about 50 moves to solve a Rubik’s Cube. Credit: Steve Zylius / UCI

“But these systems are not really intelligent; they’re brittle, and you can easily break or fool them,” Baldi said. “How do we create advanced AI that is smarter, more robust and capable of reasoning, understanding and planning? This work is a step toward this hefty goal.”

Source: Science Daily

About the Author
BS/MS
Nouran is a scientist, educator, and life-long learner with a passion for making science more communicable. When not busy in the lab isolating blood macrophages, she enjoys writing on various STEM topics.
You May Also Like
OCT 11, 2022
Genetics & Genomics
Revealing the Genome Carried by the Common Ancestor to all Mammals
OCT 11, 2022
Revealing the Genome Carried by the Common Ancestor to all Mammals
Every mammal that is found on our planet is descended from one common ancestor, thought to have lived around 180 million ...
OCT 16, 2022
Space & Astronomy
Astrobiology and Broccoli Gas
OCT 16, 2022
Astrobiology and Broccoli Gas
In a recent study published in The Astrophysical Journal, a team of researchers led by the University of California at R ...
OCT 31, 2022
Technology
Blood Test for Diagnosing Alzheimer's
OCT 31, 2022
Blood Test for Diagnosing Alzheimer's
Alzheimer’s is a debilitating neurological condition that affects about six million American adults, according to ...
NOV 10, 2022
Space & Astronomy
Hey Star, Want to Look Younger? Get Yourself a Hot Jupiter!
NOV 10, 2022
Hey Star, Want to Look Younger? Get Yourself a Hot Jupiter!
A new study published in the Monthly Notices of the Royal Astronomical Society finds that “hot Jupiter” exop ...
NOV 23, 2022
Earth & The Environment
The Ecological Impact of Wind Energy
NOV 23, 2022
The Ecological Impact of Wind Energy
In a recent study published in Biological Conservation, an international team of researchers led by UC Santa Cruz examin ...
NOV 21, 2022
Space & Astronomy
Neutron Star Structure Could be Similar to Chocolate Pralines
NOV 21, 2022
Neutron Star Structure Could be Similar to Chocolate Pralines
A group of scientists at the Goethe University Frankfurt recently published two articles about their work on determining ...
Loading Comments...