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
  • Nouran earned her BS and MS in Biology at IUPUI and currently shares her love of science by teaching. She enjoys writing on various topics as well including science & medicine, global health, and conservation biology. She hopes through her writing she can make science more engaging and communicable to the general public.
You May Also Like
DEC 03, 2019
Genetics & Genomics
DEC 03, 2019
A New Tool for Evaluating Millions of Genetic Sequences at Once
Gene sequencing technologies have created a wealth of data, and scientists can now do more with all that information....
DEC 03, 2019
Space & Astronomy
DEC 03, 2019
Will ISRO Succeed At Building its Own Space Station?
When hearing the words “space station,” the International Space Station probably comes to mind; but the International Space Station wasn’...
DEC 15, 2019
Space & Astronomy
DEC 15, 2019
Boeing's Starliner Capsule 'Ready' for First Test Flight
NASA is enthusiastic about bringing crewed space launches back to American soil very soon, and with the help of its Commercial Crew program, at least two s...
JAN 09, 2020
Technology
JAN 09, 2020
Advancing Wearable Technology
Scientists have developed a sensor that works to record the complex sensations of human skin. The development is dubbed as the ‘artificial ionic skin...
JAN 15, 2020
Technology
JAN 15, 2020
Can A Computer Identify You By How You Dance?
We have heard of face and voice recognition software programs that work to ensure the identity of someone. But, now researchers are indicating that the way...
FEB 07, 2020
Technology
FEB 07, 2020
Flyception 2.0: Tracks Complex Social Behavior of Flies
Researchers at the University of California San Diego now have a better understanding of the social behavior of insets thanks to advanced imaging technolog...
Loading Comments...