Work is step toward advanced AI systems that can think, reason, plan and make decisions
Since its invention by a Hungarian architect in 1974, the Rubik’s Cube has furrowed the brows of many who have tried to solve it, but the 3D logic puzzle is no match for an artificial intelligence system created by researchers at the University of California, Irvine.
DeepCubeA, a deep reinforcement learning algorithm programmed by UCI computer scientists and mathematicians, can find the solution in a fraction of a second, without any specific domain knowledge or in-game coaching from humans. This is no simple task considering that the cube has completion paths numbering in the billions but only one goal state – each of six sides displaying a solid color – which apparently can’t be found through random moves.
For a study published today in Nature Machine Intelligence, the researchers demonstrated that DeepCubeA solved 100 percent of all test configurations, finding the shortest path to the goal state about 60 percent of the time. The algorithm also works on other combinatorial games such as the sliding tile puzzle, Lights Out and Sokoban.
“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 researchers were interested in understanding how and why the AI made its moves and how long it took to perfect its method. They started with a computer simulation of a completed puzzle and then scrambled the cube. Once the code was in place and running, DeepCubeA trained in isolation for two days, solving an increasingly difficult series of combinations.
“It learned on its own,” Baldi noted.
There are some people, particularly teenagers, who can solve the Rubik’s Cube in a hurry, but even they take about 50 moves.
“Our AI takes about 20 moves, most of the time solving it in the minimum number of steps,” Baldi said. “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.”
The veteran computer scientist said the ultimate goal of projects such as this one is to build the next generation of AI systems. Whether they know it or not, people are touched by artificial intelligence every day through apps such as Siri and Alexa and recommendation engines working behind the scenes of their favorite online services.
“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.”
The Latest on: Deep learning algorithm
via Google News
The Latest on: Deep learning algorithm
- AI chatbot creator to discard data, algorithmson January 15, 2021 at 3:09 am
The South Korean developer of a controversial female chatbot said on Friday that it will discard all data and learning algorithms used in training the artificial intelligence (AI) platform amid ...
- AI chatbot creator to discard data, algorithms used in controversial personaon January 14, 2021 at 11:18 pm
The South Korean developer of a controversial female chatbot said Friday it will discard all data and learning algorithms used in training the artificial intelligence (AI) platform amid mounting ...
- Deep Learning May Detect Breast Cancer Earlier than Radiologistson January 14, 2021 at 6:32 am
A deep learning algorithm accurately detected breast cancer in mammography images and generalized well to populations not represented in the training dataset.
- Sensyne Health launches MagnifEye smartphone application to automate the reading and Big Data analysis of lateral flow tests using deep learning AIon January 14, 2021 at 3:53 am
Sensyne Health launches MagnifEye smartphone application to automate the reading and Big Data analysis of lateral flow tests using deep learning AI MagnifEye™ uses a cloud-based deep learning ...
- Wearable heart monitors and deep learning can provide early warning of SARS-CoV-2 infectionon January 11, 2021 at 10:03 pm
A recent study, appearing as a preprint on the medRxiv* server, reveals the possibility of early prediction of SARS-CoV-2 infection using data on the resting heart rate in the presymptomatic period.
- Mammography expert finds deep-learning artificial intelligence may improve cancer detectionon January 11, 2021 at 8:10 am
The journal Nature Medicine has published a study co-authored by Gopal Vijayaraghavan, MD, finding that an artificial intelligence model for computer-aided reading of mammograms may improve the ...
- Bengaluru: IISc, TalentSprint launch advanced certification program in 'Deep Learning'on January 9, 2021 at 4:59 pm
The Indian Institute of Science (IISc) and TalentSprint, an EdTech firm, on Saturday announced the launch of a PG level advanced certification program in Deep Learning ...
- MIT Deep-Learning Algorithm Finds Hidden Warning Signals in Measurements Collected Over Timeon January 9, 2021 at 11:29 am
A new deep-learning algorithm could provide advanced notice when systems — from satellites to data centers — are falling out of whack. When you’re responsible for a multimillion-dollar satellite ...
- IISc Announces A New PG Programme In Deep Learningon January 7, 2021 at 5:18 am
This 10-month executive program is designed for aspiring and practising AI/ML professionals who want to build expertise in deep learning.
- Deep Learning Market 2020 Growth and Forecast Survey Till 2026on January 5, 2021 at 11:28 pm
Deep Learning is a subfield of machine learning concerned with algorithms inspired by the structure and function of the ...
via Bing News