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 Algorithm Can Detect COVID-19 on Chest X-Rayson November 26, 2020 at 12:30 pm
(HealthDay News) — An artificial intelligence (AI) algorithm can detect COVID-19 on chest X-rays with similar performance to that of a consensus of thoracic radiologists, according to a study ...
- Deep learning, facial recognition, and bears: Researchers take a high-tech approach to wildlife monitoringon November 24, 2020 at 10:52 am
The BearID Project is using deep learning to help automate time-intensive research processes amid climate change and shifting wildlife behaviors.
- Binarized neural networks show promise for fast, accurate machine learningon November 24, 2020 at 5:14 am
As anyone with a green thumb knows, pruning can promote thriving vegetation. A snip here, a snip there, and growth can be controlled and directed for a more vigorous plant.
- IIT Ropar and NPTEL invite applications for Free Online Course on Deep Learningon November 19, 2020 at 4:00 pm
IIT Ropar has organised this course as deep Learning has received a lot of attention over the past few years and has been employed successfully by companies like Google, Microsoft, IBM, Facebook, ...
- Deep learning enables automated screening for diabetic retinopathyon November 18, 2020 at 12:05 pm
The deep learning method makes automated screenings for eye diseases such as diabetic retinopathy more efficient, as it reduces the amount of expensive annotated image data that is required for the ...
- System Brings Deep Learning to IoT Deviceson November 16, 2020 at 4:00 pm
Deep learning is everywhere. This branch of artificial intelligence curates your social media and serves your Google search results. Soon, deep learning could also check your vitals or set your ...
- Bringing Deep Learning to the "Internet of Things"on November 16, 2020 at 3:09 am
MIT researchers have developed a system that could bring deep learning neural networks to new – and much smaller – places, like the tiny computer chips in wearable medical devices, household ...
- Deep-learning-based algorithm helps radiologists detect cerebral aneurysmson November 11, 2020 at 3:49 am
Right: volume-rendered 3D reconstruction image. The aneurysm was missed in the initial report but successfully detected with the deep-learning algorithm. (Courtesy: Radiological Society of North ...
- Numenta Demonstrates 50x Speed Improvements on Deep Learning Networks Using Brain-Derived Algorithmson November 10, 2020 at 7:00 am
Numenta announced a technology demonstration showing their brain-derived sparse networks perform inference tasks 50x faster than dense networks.
- Estimating the carbon footprint of deep learning algorithmson November 7, 2020 at 6:24 am
According to their estimates, hardware used to train a deep learning algorithm can use worrying amounts of energy from an environmental standpoint. Whether browsing movies suggested by Netflix ...
via Bing News