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
[google_news title=”” keyword=”artificial intelligence systems” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Artificial intelligence systems
- Olympic AI? The IOC says artificial intelligence will protect athletes from online abuse at Paris Gameson May 9, 2024 at 3:33 pm
The IOC is using artificial intelligence during the Paris Olympics to monitor social media for instances of abuse against athletes competing in the 2024 Summer Games.
- Artificial Intelligence (AI) predicts list of animals capable of taking over Earth; Details hereon May 9, 2024 at 2:09 pm
A question to Chat-GPT on animals that are capable of taking over Earth reveals some interesting option. The planet of Apes type scenario is an interesting scenario, which Artificial Intelligence (AI) ...
- Safety Shield Global’s AI Safety System Secures King’s Award for Enterpriseon May 9, 2024 at 11:13 am
Safety Shield Global wins King’s Award for Enterprise with its AI system, achieving 99.6% accuracy in preventing construction site accidents.
- Artificial intelligence and art: The group trying to get AI to read our mindson May 9, 2024 at 10:32 am
Obvious, consisting of a group of three digital artists working on AI, is a project that borders art and science: An exploration of AI's ability to translate our imagination onto the canvas.
- Top Stock Movers Now: Equinix, Epam Systems, Roblox, and Moreon May 9, 2024 at 9:40 am
U.S. equities were higher at midday Thursday, May 9, 2024, as rising unemployment claims lifted hopes the Fed would move to lower interest rates.
- Explainer: How dependent is China on US artificial intelligence technology?on May 9, 2024 at 7:29 am
The Biden administration plans to put guardrails on U.S.-developed artificial intelligence (AI) models that power popular chatbots like ChatGPT to safeguard the technology from countries such as China ...
- 2 Millionaire-Maker Artificial Intelligence (AI) Stockson May 9, 2024 at 1:55 am
Snowflake ( SNOW -0.82%) and Super Micro Computer ( SMCI 0.41%) have become pivotal in the development and growth of artificial intelligence (AI) technology. These stocks have the ingredients to ...
- Artificial Intelligenceon May 8, 2024 at 4:33 am
The system, AlphaFold3 ... start-up is also joining an industrywide effort to spot content made with artificial intelligence. By Cade Metz and Tiffany Hsu The suit, which accuses the tech ...
- Cisco Systems CEO says his company is ready to leverage artificial intelligenceon May 8, 2024 at 3:57 am
Cisco Systems Inc. chief executive officer Chuck Robbins says the company missed a major opportunity to expand 10 years ago as cloud computing took off. But he insists it won’t make that mistake again ...
- JAMS Issues Rules Governing Disputes Involving Artificial Intelligence Systemson May 7, 2024 at 5:00 pm
The Artificial Intelligence Group at Ballard Spahr monitors developments ... of the guidelines is to “refine and clarify procedures for cases involving AI systems,” and to “equip legal professionals ...
via Bing News