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 of 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 mechanism. 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) rechecking CL from the level of artificial general intelligence; ii) providing a detailed and extensive overview on CL topics; iii) presenting some novel ideas on the potential development of CL.

arXiv comment21 pages, 10 figures

References in corpus (25)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Auto-Encoding Variational Bayes
• Distilling the Knowledge in a Neural Network
• Overcoming catastrophic forgetting in neural networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Generative Adversarial Networks: An Overview
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• Continual Learning Through Synaptic Intelligence
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
• Efficient Lifelong Learning with A-GEM
• Three scenarios for continual learning
• Overcoming Catastrophic Forgetting by Incremental Moment Matching
• Generative replay with feedback connections as a general strategy for continual learning
• Fast Context Adaptation via Meta-Learning
• Towards Robust Evaluations of Continual Learning
• Less-forgetting Learning in Deep Neural Networks
• Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data
• DSD: Dense-Sparse-Dense Training for Deep Neural Networks
• Continual Learning in Generative Adversarial Nets
• Neurogenesis Deep Learning
• Task Agnostic Continual Learning via Meta Learning
• La-MAML: Look-ahead Meta Learning for Continual Learning
• An Adaptive Random Path Selection Approach for Incremental Learning
• Meta-learnt priors slow down catastrophic forgetting in neural networks
• Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation