Lifelong Learning at the Edge: Algorithms and Foundations

Lifelong Learning (or Lifelong Machine Learning) is an advanced Machine Learning (ML) paradigm: an architecture for ML systems that learn continuously, accumulate knowledge learned in the past, and use that knowledge to help future learning and problem solving. This talk will explore three aspects of Lifelong Learning.

Lifelong Learning can reduce up-front energy consumption in the model training process, because it can use a signal propagation approach that combines learning into the inference process and enables the system to add classes to its knowledge model at the same time it is being used to solve problems. Lifelong Learning includes new mechanisms that can make the AI temporally aware, mechanisms which can improve the system's ability to work effectively with limited data. Lifelong Learning research is also exploring new models of computation – “Super-Turing computation,” a model of computation that resembles biological learning.

Dr. Hava Siegelmann is a Provost Professor of the University of Massachusetts and Director of the Biologically Inspired Neural and Dynamical Systems (BINDS) Laboratory.

This talk was the May 2024 meeting of ACM Princeton Chapter