New Project Hopes to Make Independent AI Systems Learn from Each Other

The aim behind a new international project is to develop advanced AI programs that will allow machines to learn gradually over a lifetime and share that input with each other.

New Project Hopes to Make Independent AI Systems Learn from Each Other.

Image Credit: Loughborough University.

Scientists are optimistic that the technology will enable machines to reuse data, adapt rapidly to new conditions and work in partnership by sharing data.

The project comes under the initiative known as Shared-Experience Lifelong Learning (ShELL), a program financially supported by the Defense Advanced Research Projects Agency (DARPA) — a U.S. government agency known for some major technological developments in recent history such as the Internet, Siri, the miniaturization of GPS and the computer mouse.

It began this month and is being headed by Dr. Andrea Soltoggio of Loughborough’s Computer Science department, in partnership with Dr. Soheil Kolouri at Vanderbilt University and Dr. Cong Liu at the University of Texas at Dallas, both in the United States.

The idea behind this project is to gain a deep understanding of how and what an AI system learns when dealing with a new task, so that we can exploit task similarities and share information to create fast, reliable, and collaborating learning agents.

Dr. Andrea Soltoggio, Department of Computer Science, Loughborough University

One exciting aspect that goes beyond pure technological advances is that this research addresses high-level questions. How can individual entities share information and benefit from each other’s experiences when learning together?” added Dr. Soltoggio.

If one agent makes mistakes while learning a task, can this experience be shared with other agents so that they don’t make the same mistakes? Currently, these questions are mostly unanswered, but our proposal sets out lines of investigation to create such learning processes within AI agents.

Dr. Andrea Soltoggio, Department of Computer Science, Loughborough University

Each university participating in the project will work on different areas of lifelong learning, a comparatively new area of machine learning research that has also developed with the efforts of the preceding Lifelong Learning Machines (L2M) DARPA program.

Loughborough will concentrate on unique bio-inspired neural networks that learn shareable knowledge, taking advantage of neuromodulation and synaptic consolidation mechanisms.

Vanderbilt University will focus on the statistical foundation of the learning mechanisms and algorithmic theory, while Texas University will look at the hardware integration and utilization for possible transition to industrial and practical applications.

The real-world applications of this new technology could include co-operating self-learning driver-less vehicles such as robotic rescue and exploration systems, distributed monitoring systems to detect emergencies, self-driving cars or cyber security systems of agents that track large networks.

The financial support is part of DARPA’s Artificial Intelligence Exploration (AIE) program — an efficient research and development scheme aimed at boosting rapid innovations in quickly accelerating technology.

This funding from DARPA represents a phenomenal success for the University. It recognises the international standing of our AI experts and Dr Soltoggio’s position among the leading authorities in the world on AI.

Claudia Eberlein, Professor and Dean of School of Science, Loughborough University


Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type