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
- Graph Learning: A Surveyon May 2, 2021 at 9:01 am
Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a wide spectrum of application domains such as social systems, ecosystems, ...
- Local Alignment of DNA Sequence Based on Deep Reinforcement Learningon May 1, 2021 at 11:11 am
Goal: Over the decades, there have been improvements in the sequence alignment algorithm, with significant advances in various aspects such as complexity and accuracy. However, human-defined ...
- Smiths Detection Launches Lithium Batteries Algorithm for Cargo and Checked Baggage Systemon April 30, 2021 at 6:31 am
Smiths Detection has launched a new lithium batteries algorithm for the HI-SCAN 10080 EDX-2is, its dual-view air cargo and checked-baggage screening system. The algorithm has been designed to provide ...
- Dynamic Yield's Deep Learning Product Recommendations Generate Exponential Revenue Returnson April 28, 2021 at 8:00 am
Dynamic Yield, the Experience Optimization platform, today announced the gradual release of its state-of-the-art, self-training Deep ...
- A calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographson April 27, 2021 at 7:11 am
Musculoskeletal disorders are injuries or pain in the human musculoskeletal system, including the joints, ligaments, muscles, nerves, tendons, and structures that support the limbs, neck, and back.
- Machine learning and deep learning to predict mortality in patients with spontaneous coronary artery dissectionon April 26, 2021 at 3:20 pm
Machine learning (ML) and deep learning (DL) can successfully predict high prevalence events in very large databases (big data), but the value of this methodology for risk prediction in smaller ...
- Smiths Detection Provides Automatic Detection of Lithium Batteries with Algorithm for Hi-Scan 10080 EDX-2ison April 26, 2021 at 11:43 am
Smiths Detection announced it has launched a new lithium batteries algorithm for the HI-SCAN 10080 EDX-2is, its dual-view air cargo and checked-baggage screening system. The algorithm will provide ...
- A Better Way to Spot Deep-Faked Satellite Imageson April 26, 2021 at 8:10 am
Computer-generated satellite “photos” can be very difficult for humans and other machine learning algorithms to detect, a growing concern of national security officials who fear that doctored images ...
- Algorithms to Antenna: Labeling Radar and Comms Signals for Deep-Learning Appson April 22, 2021 at 10:04 pm
Previous blogs on deep learning focused on applying techniques to various radar and communications applications. Here we look at labeling the real-world data gathered from a radar, radio, or ...
- Adversarial machine learning: The underrated threat of data poisoningon April 21, 2021 at 11:40 pm
Researchers warn machine learning models are vulnerable to data poisoning, which can result in poor decisions based on faulty outputs.
via Bing News