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
- Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizationson January 30, 2020 at 2:12 pm
We address this problem by developing hidden fluid mechanics (HFM), a physics-informed deep learning framework capable of encoding the Navier-Stokes ... the right panels we plot the corresponding ...
- Opening the AI box: can deep learning predict cancer recurrence?on January 29, 2020 at 2:13 am
The deep-learning algorithm automatically annotates a 3D whole-mount pathology image and presents the discovered features in an understandable way. The patches with high probability of cancer ...
- Two deals in a week: ServiceNow acquires Passage AI for its deep learning chatbotson January 28, 2020 at 9:14 am
But what apparently drew ServiceNow’s attention was the platform’s support for multiple languages. The deep learning algorithms that Passage AI uses to power chatbots aren’t pre-calibrated, but rather ...
- European researchers look beyond deep learningon January 28, 2020 at 8:56 am
Just a couple of years after the first papers on deep learning appeared in 2006, a team at Stanford University showed how you could get a 70-fold speed boost over a regular dual-core Intel x86 ...
- Yogi Closes $2.3M Seed Financing to Expand Its Deep Learning Customer Feedback Analytics Platformon January 27, 2020 at 6:15 am
Yogi, a customer feedback analytics platform deploying deep learning for actionable product insights ... The Yogi platform is centered on advanced and scalable natural language processing algorithms, ...
- Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Riskon January 24, 2020 at 5:06 am
to leverage the interpretability of attention layers combined with Bayesian deep learning to gain a better understanding of intensive-care patients at increased risk of readmission. The algorithms ...
- Deep learning to distinguish benign from malignant renal lesions based on routine MR imaging.on January 24, 2020 at 12:21 am
Among the 1162 renal lesions, 655 were malignant and 507 were benign. Compared to a baseline zero rule algorithm, the ensemble deep learning model had a statistically significant higher test accuracy ...
- Deep Learning Predicts Disease-Related Mutationson January 23, 2020 at 5:16 pm
Scientists in Hong Kong and the US have developed a deep learning approach to predict mutations in the ... researchers are relying on computational algorithms to obtain actionable insights for ...
- Healthcare Algorithms Are Biased, and the Results Can Be Deadlyon January 23, 2020 at 8:12 am
Deep-learning algorithms suffer from a fundamental problem: They can adopt unwanted biases from the data on which they're trained. In healthcare, this can lead to bad diagnoses and care ...
- Deep Learning Enables Imaging Around Cornerson January 23, 2020 at 2:41 am
Short exposure times are necessary for real-time imaging but produce too much noise for existing algorithms to work. To solve this problem, the researchers turned to deep learning. "Compared to other ...
via Bing News