
Abstract design made of head outlines, lights and abstract design elements on the subject of intelligence, consciousness, logical thinking, mental processes and brain power
Researchers have developed a new framework for deep neural networks that allows artificial intelligence (AI) systems to better learn new tasks while “forgetting” less of what they have learned regarding previous tasks.
The researchers 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.
“People are capable of continual learning; we learn new tasks all the time, without forgetting what we already know,” says Tianfu Wu, an assistant professor of electrical and computer engineering at NC State and co-author of a paper on the work. “To date, AI systems using deep neural networks have not been very good at this.”
“Deep neural network AI systems are designed for learning narrow tasks,” says 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.”
“We have proposed a new framework for continual learning, which decouples network structure learning and model parameter learning,” says Yingbo Zhou, co-lead author of the paper and a research scientist at Salesforce Research. “We call it the Learn to Grow framework. In experimental testing, we’ve found that it outperforms previous approaches to continual learning.”
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 datasets, 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 says. “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,” says 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.”
Learn more: Framework Improves ‘Continual Learning’ For Artificial Intelligence
The Latest on: Continual learning for artificial intelligence
via Google News
The Latest on: Continual learning for artificial intelligence
- Teradyne and Syntiant Collaborate to Significantly Shorten Time to Market for Innovative Artificial Intelligence Neural Decision Processorson January 12, 2021 at 6:20 am
Neural Decision Processors™ to customers worldwide. Built from a clean sheet, hardware/software co-design methodology that optimizes silicon and deep learning models together, the Syntiant ® NDP100™ ...
- Artificial Intelligence Ai In Market Growth Factors, Trends, Consumption, Production, Revenue and Forecast 2020-2023on January 7, 2021 at 5:13 am
The global AI in marketing market is segmented into various segments on the basis of deployment, technology, applications, and verticals. The GLOBAL Artificial Intelligence (AI) in Marketing Market is ...
- Artificial Intelligence arrives January 16 at Discovery Place Scienceon January 5, 2021 at 4:55 am
CHARLOTTE — If artificial intelligence ... about the concept of man-made intelligence. They can also see how the human brain goes through the process of learning and compare it to how machines ...
- How Machine Learning, Artificial Intelligence Anticipate Cryptocurrency Price?on January 4, 2021 at 9:50 pm
The popularity of cryptocurrencies skyrocketed in 2017 due to a few continuous months of an exponential development of their showcase capitalization. The ...
- Healthcare Artificial Intelligence Market Detailed Analysis of Current Industry Figures with Forecasts Growth By 2025on January 4, 2021 at 6:42 am
Request a sample Report of Healthcare Artificial Intelligence Market Analysis Report at: Growing applications of AI for healthcare and research purposes, including detection of disease, management of ...
- Artificial Intelligence Market World-Wide Industry Trends, Entry Strategies, Regulatory Frameworks and Technologies till 2026on December 26, 2020 at 5:38 am
"Artificial ... intelligence (AI) market on the basis of components, technology, industry vertical, and geography. In terms of technology, the market is divided into machine learning, computer ...
- Enterprise Artificial Intelligence Marketon December 21, 2020 at 10:35 pm
machine learning, predictive analytics, automated data science, and automation to aid with a solution for various organizations. The market for enterprise artificial intelligence is estimated to ...
- Artificial intelligence sets sights on the sunon December 14, 2020 at 10:43 am
Continuous monitoring of the Sun is essential ... In their recent study, the researchers used artificial intelligence (AI) to achieve quality assessment that is similar to human interpretation.
- Global Artificial Intelligence in Diagnostics Market 2020 Industry Dynamics, Segmentation and Competition Analysis 2027on December 3, 2020 at 8:00 pm
Moreover, continuous advancements in artificial intelligence and deep learning are expected to prove more efficient in identifying disease diagnosis over the upcoming years. Get Sample Copy of ...
- eLearningClasses.com An Online Academy Powered by Artificial Intelligence & Human Instructors Launchedon September 4, 2020 at 7:21 am
Global Banking & Finance Review launched its e-learning platform called eLearning ... eLearningClasses.com is an innovative online academy powered by artificial intelligence and real human ...
via Bing News