Reviewing continual learning from the perspective of human-level intelligence

Abstract

Humans continual learning (CL) ability is closely related to Stability Versus Plasticity Dilemma that describes how humans achieve ongoing learning capacity and preservation for learned information. The notion of CL has always been present in artificial intelligence (AI) since its births. This paper proposes a comprehensive review on CL. Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechansim. Analogous to biological counterpart, "smart" AI agents are supposed to i) remember previously learned information (information retrospection); ii) infer on new information continuously (information prospection:); iii) transfer useful information (information transfer), to achieve high-level CL. According to the taxonomy, evaluation metrics, algorithms, applications as well as some open issues are then introduced. Our main contributions concern i) recheck CL from the level of artificial general intelligence; ii) provide a detailed and extensive overview on CL topics; iii) present some novel ideas on the potential development of CL.

An empirical comparison of generators in replay-based continual learning

“…Generative replay (or: pseudo-rehearsal) for CL has been the subject of numerous articles, see, e.g., [1,[6][7][8] for reviews or [9] for the original article. Benchmarks of replay approaches are performed in, e.g., [10] or [5].…”