Continual Learning

Mohammad Derakhshani (Ph.D. Student)

Despite the promise of artificially intelligent agents, they are known to suffer from catastrophic forgetting when learning over nonstationary data distributions. Continual learning, also known as life-long learning, was introduced to deal with catastrophic forgetting. In this framework, an agent continually learns to solve a sequence of non-stationary tasks by accommodating new information, while remaining able to complete previously experienced tasks with minimal performance degradation. The fundamental challenge in continual learning is catastrophic forgetting. Our project aims at solving catastrophic forgetting from different perspectives such as optimization, deep neural network design and etc.

Primary Advisor:	Cees Snoek (University of Amsterdam)
Industry Advisor:	Xiantong Zhen (University of Amsterdam & Inception Institute of Artificial Intelligence)
PhD Duration:	01 January 2020 - 31 December 2023