Distributed and Time-Aware Continual Learning

Abstract

This research plan aims to produce human-like time-awareness in deep neural networks, which helps avoid catastrophic forgetting. Wepropose a dynamically adaptive structural deep model with memory and an internal clock that stores the essence of old memories withtheir corresponding time information and transfers the previous model parameters to a new task presented at a given time.We furtherdevise algorithms and protocols for distributed continual learning. We consider the setting where a number of continual learning agents can share information and learn from each other to improve their performance on newly arriving unseen tasks that other agents could have seen. These protocols and algorithms are specially designed to address the issues brought by limited computation and communication resources.

Document Details

Document Type
DoD Grant Award
Publication Date
Jul 24, 2023
Source ID
N000142312629

Entities

People

  • Hoda Bidkhori

Organizations

  • George Mason University
  • Office of Naval Research
  • United States Navy

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Artificial Intelligence
  • Computer Networking

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks