Back to search

Rochester Institute of Technology

Towards Efficient Continual Deep Learning

Abstract

dc:description.abstract

Modern AI systems can achieve remarkable performance on tasks such as image recognition, object detection, and language understanding, but they often struggle with a basic ability that humans rely on every day: learning continuously. When deep neural networks (DNNs) are updated with new information, they can unexpectedly forget what they previously learned, making them difficult to deploy in changing real-world environments. This dissertation explores how to build AI systems that can learn more like humans: adapting to new data, preserving past knowledge, and using prior experience to learn future tasks more efficiently. Rather than focusing only on preventing forgetting, this work also addresses two critical requirements for practical continual learning (CL): computational efficiency and forward transfer. The dissertation introduces several methods that improve how DNNs learn from evolving data streams, including biologically inspired wake/sleep training, efficient rehearsal strategies, techniques for reducing stability gap, and approaches for improving out-of-distribution (OOD) generalization (i.e., forward transfer) and detection. Together, these contributions move CL closer to real-world deployment by making AI systems more efficient, adaptable, and reliable in open-world environments. The broader goal of this work is to help develop machine learning systems that can keep improving over time without the costly need to repeatedly retrain from scratch.

Degree

thesis:*
Name thesis:degree_name
Imaging Science (Ph.D.)
Level thesis:degree_level
Dissertation
Discipline thesis:degree_discipline
Chester F. Carlson Center for Imaging Science

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Harun, Md Yousuf
Contributors dc:contributor
  • Christopher Kanan,

Subjects

dc:subject × 3

Identifiers

dc:identifier.*
Repository record dc:identifier
https://repository.rit.edu/theses/12688

Chain of custody

source
Harvested from
Rochester Institute of Technology
Base URL
repository.rit.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Harun, Md Yousuf. Towards Efficient Continual Deep Learning. Dissertation thesis, https://repository.rit.edu/theses/12688