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
- ChatGPT may reset the world of work as businesses rush to own artificial intelligenceon February 9, 2023 at 1:00 am
Businesses have profited by owning the factories and machinery, but as artificial intelligence systems like ChatGPT strut their stuff, companies are rushing to own a sort of brain power too. Where ...
- Artificial Intelligence to be a game changer in government audit space: CAGon February 8, 2023 at 10:45 pm
The potential benefits of applying AI techniques to the audit processes are substantial/ and have already been identified through several use cases, he said in his closing remarks at the SCO SAI ...
- Artificial Intelligence Take-Over: Rashid Khanon February 8, 2023 at 9:21 pm
The co-founders are investing in growth in new geographies, product development and scaling operations ahead of the curve ...
- Artificial Intelligence-based Cybersecurity Market 2023 Size Industry, Current Trends, Demand and Size Share Estimation by 2029 with Top Playerson February 8, 2023 at 7:36 pm
This report focuses on the Artificial Intelligence-based Cybersecurity Market sales, revenue, market share and industry ranking of main manufacturers, data. Identification of the ...
- Artificial Intelligence (AI) in Manufacturing Market 2023 Size Industry, Current Trends, Demand and Size Share Estimation by 2029 with Top Playerson February 8, 2023 at 7:34 pm
Artificial Intelligence (AI) in Manufacturing Market Size 2023-2029 | New Report (123 Pages) | In This Reports ...
- Report outlines artificial intelligence cyber risks, solutions for health careon February 8, 2023 at 12:53 pm
According to the paper, artificial intelligence systems, especially those dependent on machine learning, can be vulnerable to intentional attacks that involve evasion, data poisoning, model ...
- Artificial Intelligence challenges in Business Educationon February 8, 2023 at 6:36 am
As education evolves, researchers are applying advanced AI techniques, i.e. deep learning, data mining, etc., to deal with complex learning issues and customize teaching methods for individual ...
- Artificial Intelligence (AI) Chip Market Size to Surpass USD 227.48 BN by 2032on February 8, 2023 at 6:26 am
Artificial intelligence chips are designed to support deep-learning ... Increasing demand for potential systems to manage patient data is considered to drive the growth of the healthcare segment ...
- Artificial Intelligence Is Going To Be a Game Changer In Audit Space, Says Government Auditor G C Murmuon February 7, 2023 at 11:29 pm
Murmu reportedly highlighted that it's again crucial for SAIs to build the necessary skills to examine information system controls, given the shift to electronic processing and computerized systems in ...
- Artificial intelligence systems will lead to layoffs, but traders say they will be fineon February 6, 2023 at 9:55 am
Advanced artificial intelligence systems are expected to eventually replace some jobs in the financial, media, legal and technology sectors, according to the latest MLIV Pulse survey.
via Bing News