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
- Global Artificial Intelligence (Ai) In Manufacturing Market Trends 2020 | Segmentation, Outlook, Industry Report to 2026on April 12, 2021 at 6:53 am
Global artificial intelligence ai in manufacturing market is estimated to grow at a CAGR of 33 5 during the forecast period 2019 2025 The global AI in manufacturing market value was nearly 3 billion ...
- Career roadmap: Artificial Intelligence Engineeron April 12, 2021 at 3:00 am
It's a safe bet that possessing skills related to artificial intelligence (AI ... cyber attacks against our nascent F-22 fleet." "If you stop learning you pass quickly into irrelevancy, so continuing ...
- AI Weekly: Continual learning offers a path toward more humanlike AIon April 9, 2021 at 9:30 pm
Continual learning might offer a path toward more human-like AI, the members of nonprofit research group ContinualAI believe.
- Ability of artificial intelligence to detect T1 esophageal squamous cell carcinoma from endoscopic videos and the effects of real-time assistanceon April 8, 2021 at 7:51 am
Diagnosis using artificial intelligence (AI) with deep learning could be useful in endoscopic examinations ... The AI diagnosing system recognized 30 continuous frames of still images in 1 s of video ...
- Active Learning: Adding a Human Element to Artificial Intelligence, Machine Learning & Cybersecurityon April 5, 2021 at 6:21 am
"This time it's different," and AI would make it all better, and "no-code" AI/ML deep-learning adversarial recurrent network ... for the techniques pioneered in the "big data" and "artificial ...
- Artificial intelligence, game-based techniques to take lead in new education boardon March 30, 2021 at 12:10 pm
The Delhi government plans to introduce the use of Artificial Intelligence (AI) and game-based techniques for continuous assessment ... to ensure a personalised learning experience for our students.
- How Hospitality Sector is relying on artificial intelligence and machine learning for profit maximizationon March 26, 2021 at 3:33 am
Therefore, companies in the hospitality sector must adopt AI and ML for ensuring continuous delivery of their ... by ensuring a more profitable business. Both Artificial Intelligence and Machine ...
- Absorb Software Launches Next-Gen Administration and Learning Through New AI Suite: Absorb Intelligence™on March 23, 2021 at 12:00 am
provider of the Absorb Learning Management System (LMS), Absorb Infuse and Absorb Create, today announced the release of a new suite of artificial intelligence tools named Absorb Intelligence TM.
via Bing News