A project of the U.S. Army has developed a new framework for deep neural networks that allows artificial intelligence systems to better learn new tasks while forgetting less of what they have learned in previous tasks.
The North Carolina State University researchers, funded by the Army, have also demonstrated that using the framework to learn a new task can make the AI better at performing previous tasks, a phenomenon called backward transfer.
“The Army needs to be prepared to fight anywhere in the world so its intelligent systems also need to be prepared,” said Dr. Mary Anne Fields, program manager for Intelligent Systems at Army Research Office, an element of U.S. Army Combat Capabilities Development Command’s Army Research Lab. “We expect the Army’s intelligent systems to continually acquire new skills as they conduct missions on battlefields around the world without forgetting skills that have already been trained. For instance, while conducting an urban operation, a wheeled robot may learn new navigation parameters for dense urban cities, but it still needs to operate efficiently in a previously encountered environment like a forest.”
The research team proposed a new framework, called Learn to Grow, for continual learning, which decouples network structure learning and model parameter learning. In experimental testing it outperformed previous approaches to continual learning.
“Deep neural network AI systems are designed for learning narrow tasks,” said Xilai Li, a co-lead author of the paper and a Ph.D. candidate at NC State. “As a result, one of several things can happen when learning new tasks, systems can forget old tasks when learning new ones, which is called catastrophic forgetting. Systems can forget some of the things they knew about old tasks, while not learning to do new ones as well. Or systems can fix old tasks in place while adding new tasks — which limits improvement and quickly leads to an AI system that is too large to operate efficiently. Continual learning, also called lifelong-learning or learning-to-learn, is trying to address the issue.”
To understand the Learn to Grow framework, think of deep neural networks as a pipe filled with multiple layers. Raw data goes into the top of the pipe, and task outputs come out the bottom. Every “layer” in the pipe is a computation that manipulates the data in order to help the network accomplish its task, such as identifying objects in a digital image. There are multiple ways of arranging the layers in the pipe, which correspond to different “architectures” of the network.
When asking a deep neural network to learn a new task, the Learn to Grow framework begins by conducting something called an explicit neural architecture optimization via search. What this means is that as the network comes to each layer in its system, it can decide to do one of four things: skip the layer; use the layer in the same way that previous tasks used it; attach a lightweight adapter to the layer, which modifies it slightly; or create an entirely new layer.
This architecture optimization effectively lays out the best topology, or series of layers, needed to accomplish the new task. Once this is complete, the network uses the new topology to train itself on how to accomplish the task — just like any other deep learning AI system.
“We’ve run experiments using several data sets, and what we’ve found is that the more similar a new task is to previous tasks, the more overlap there is in terms of the existing layers that are kept to perform the new task,” Li said. “What is more interesting is that, with the optimized — or “learned” topology — a network trained to perform new tasks forgets very little of what it needed to perform the older tasks, even if the older tasks were not similar.”
The researchers also ran experiments comparing the Learn to Grow framework’s ability to learn new tasks to several other continual learning methods, and found that the Learn to Grow framework had better accuracy when completing new tasks.
To test how much each network may have forgotten when learning the new task, the researchers then tested each system’s accuracy at performing the older tasks — and the Learn to Grow framework again outperformed the other networks.
“In some cases, the Learn to Grow framework actually got better at performing the old tasks,” said Caiming Xiong, the research director of Salesforce Research and a co-author of the work. “This is called backward transfer, and occurs when you find that learning a new task makes you better at an old task. We see this in people all the time; not so much with AI.”
“This Army investment extends the current state of the art machine learning techniques that will guide our Army Research Laboratory researchers as they develop robotic applications, such as intelligent maneuver and learning to recognize novel objects,” Fields said. “This research brings AI a step closer to providing our warfighters with effective unmanned systems that can be deployed in the field.”
Learn more: Army-funded research boosts memory of AI systems
The Latest on: Artificial intelligence systems
via Google News
The Latest on: Artificial intelligence systems
- Five Core Virtues For Data Science And Artificial Intelligenceon February 27, 2020 at 5:19 am
Roles have included co-founder at a data analytics startup, VP Data Science and AI at Booz Allen, and Global Analytics Lead at Accenture. Virtues should be digitized. As we speed toward reliance on ...
- Artificial Intelligence Market - By Supply Demand Scenario, Application, By Region, Pricing Analysis, Opportunities and Forecast 2026on February 26, 2020 at 10:16 pm
Artificial Intelligence Market top players include Alphabet (Google Inc.), Apple Inc., Baidu, IBM Corporation, IPsoft, Microsoft Corporation, MicroStrategy, Inc, NVIDIA Qlik Technologies Inc, Verint ...
- Clinical Artificial Intelligence Leader Jvion Expands Executive Team to Scale Growth and Deliver the Next in Accountable Careon February 26, 2020 at 7:15 pm
for preventing avoidable patient harm, today announced the expansion of their executive team after a year of rapid growth. The addition of industry veterans Eric Schrock as Chief Technology Officer an ...
- Why this ASX artificial intelligence share is on the move todayon February 26, 2020 at 5:33 pm
share price is moving higher today after the artificial intelligence company delivered its FY19 results. The post Why this ASX artificial intelligence share is on the move today appeared first on ...
- 12 Artificial Intelligence (AI) Milestones: 2. Ramon Llull And His ‘Thinking Machine’on February 26, 2020 at 2:28 pm
The origins of "thinking machines" and "artificial intelligence" or the origin of tools for thinking and intelligence augmentation?
- Artificial intelligence uncovers outrageous employee expense reportson February 26, 2020 at 8:53 am
But they don't find typos in invoice numbers, duplicates across expense and AP systems – or, ahem, interesting items employees bill to their employers. SEE: Cheat sheet: Artificial intelligence (free ...
- Augmented Video, Artificial Intelligence, and Machine Learning: How This Startup Lets Fans (and Teams) See Soccer in a Whole New Wayon February 26, 2020 at 7:05 am
Not data. But that's about to change. Major League Soccer (MLS) and Second Spectrum just announced a multi-year agreement; as the league's first Official Advanced Tracking Data Provider, Second ...
- Artificial Intelligence Systems Spending Market is Exhibiting a CAGR of 46.1% by 2027 | FMIon February 26, 2020 at 4:27 am
VALLEY COTTAGE, N.Y. - A new report published by Future Market Insights titled "Artificial Intelligence Systems Spending Market: Global Industry Analysis (2012 - 2016) and Opportunity Assessment (2017 ...
- Artificial intelligence startup SambaNova Systems raises $250Mon February 25, 2020 at 6:53 pm
Artificial intelligence hardware and software startup SambaNova Systems Inc. has raised $250 million in new funding to allow it to further accelerate the software capabilities of its next-generation ...
- Kantar Applies Artificial Intelligence to Your Shopping Basketon February 25, 2020 at 5:13 pm
No robots in the food aisle yet. Kantar applies Singapore-developed AI technology to the growth challenges faced by CPG brands. SINGAPORE, Feb. 26, 2020 /PRNewswire/ -- Kantar, the world's leading ...
via Bing News