Progress on Lifelong Learning Machines Shows Potential for Bio-Inspired Algorithms

“The L2M program’s prime objective is to develop systems that can learn continuously during execution and become increasingly expert while performing tasks, are subject to safety limits, and capable of applying previous skills and knowledge to new situations, without forgetting previous learning,” s...

Full description

Saved in:
Bibliographic Details
Published inECN
Format Trade Publication Article
LanguageEnglish
Published Rockaway Advantage Business Media 14.03.2019
Subjects
Algorithms
Artificial intelligence
Engineering schools
Lifelong learning
Machine learning
R&D
Research & development
Researchers
Walking
Online AccessGet full text
ISSN1523-3081

Cover

More Information
Summary:“The L2M program’s prime objective is to develop systems that can learn continuously during execution and become increasingly expert while performing tasks, are subject to safety limits, and capable of applying previous skills and knowledge to new situations, without forgetting previous learning,” said Dr. Hava Siegelmann, program manager in DARPA’s Information Innovation Office (I2O). First announced in 2017, L2M is over a year into research and development of next generation AI systems and their components, as well as learning mechanisms in biological organisms capable of translation into computational processes. Behind the USC researchers’ robotic limb is a bio-inspired algorithm that can learn a walking task on its own after only five minutes of “unstructured play” – or conducting random movements that enable the robot to learn its own structure as well as its surrounding environment.
ISSN:1523-3081