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
- Neural architecture search automates the development of deep learning-based models for cancer researchon November 18, 2019 at 12:58 pm
There is a particular need to develop deep-learning methods -; that is, machine learning algorithms capable of extracting science from unstructured data. Researchers from the U.S. Department of Energy ...
- Deep Clustering for Mars Rover image datasetson November 18, 2019 at 9:13 am
We test the performance of the algorithm on a smaller labeled dataset, and report good accuracy and concordance with the ground truth labels. This is the first attempt to use deep learning based ...
- Amazon Saw 15-Fold Jump In Forecast Accuracy With Deep Learning And Other AI Statson November 14, 2019 at 6:04 am
When Amazon switched from traditional machine learning techniques to deep learning in 2015, it saw a 15-fold increase in the accuracy ... The company’s 24-person data-science team trained ...
- Machine Learning-Based Analysis of Sperm Videos and Participant Data for Male Fertility Predictionon November 14, 2019 at 2:58 am
Our results indicate that sperm motility prediction based on deep learning using sperm motility videos is rapid to perform and consistent. Adding participant data did not improve the algorithms ...
- Deep Learning Market by Top Players -Advanced Micro Devices, ARM Ltd, Clarifai, Entilic, Google, & Moreon November 13, 2019 at 9:59 pm
Deep learning is a part of machine learning which deals with algorithms similar to the functioning of the neural system in the brain. The language has three major forms of architecture, namely ...
- Evaluating Deep Learning Methods for Identifying Nucleion November 13, 2019 at 8:26 am
The optimal approach to segmentation, which refers to the process of delimiting the boundaries of objects, is through solutions offered by deep learning solutions. This subset of machine learning ...
- Deep neural networks speed up weather and climate modelson November 13, 2019 at 1:11 am
The algorithms—called domain-aware neural networks—that consider known relationships ... "This database is unique to climate science at Argonne," said Wang, "and we are using it to conduct further ...
- Deep Learning Market to Hold a High Potential for Growth by 2026: Allied Market Researchon November 13, 2019 at 12:09 am
Nov 13, 2019 (Hitech News Daily via COMTEX) -- Deep learning is a subfield of machine learning that consist of a series of computer instructions or algorithms that is inspired by the function and ...
- Machine-learning scientist cautions against ill-considered AI deploymentson November 12, 2019 at 5:32 pm
Deep learning is a subset of machine learning, which in itself is a level under AI, Lazzeri explained. “AI is a way of building applications on top of machine-learning models, and they run on top of ...
- Optimizing in a Heterogeneous World is (Algorithms x Devices)on November 11, 2019 at 6:03 am
In this guest article, our friends at Intel discuss how CPUs prove better for some important Deep Learning. Here’s why, and keep your GPUs handy! When programming in a heterogeneous world, we need to ...
via Bing News