An Appraisal of Incremental Learning Methods

As a special case of machine learning, incremental learning can acquire useful knowledge from incoming data continuously while it does not need to access the original data. It is expected to have the ability of memorization and it is regarded as one of the ultimate goals of artificial intelligence technology. However, incremental learning remains a long term challenge. Modern deep neural network models achieve outstanding performance on stationary data distributions with batch training. This restriction leads to catastrophic forgetting for incremental learning scenarios since the distribution of incoming data is unknown and has a highly different probability from the old data. Therefore, a model must be both plastic to acquire new knowledge and stable to consolidate existing knowledge. This review aims to draw a systematic review of the state of the art of incremental learning methods. Published reports are selected from Web of Science, IEEEXplore, and DBLP databases up to May 2020. Each paper is reviewed according to the types: architectural strategy, regularization strategy and rehearsal and pseudo-rehearsal strategy. We compare and discuss different methods. Moreover, the development trend and research focus are given. It is concluded that incremental learning is still a hot research area and will be for a long period. More attention should be paid to the exploration of both biological systems and computational models.

[1]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[2]  Lifeng Sun,et al.  Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning , 2019, Neural Computation.

[3]  David Filliat,et al.  Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges , 2020, Inf. Fusion.

[4]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[5]  Pierre Alliez,et al.  Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[6]  Aida Chefrour,et al.  Incremental supervised learning: algorithms and applications in pattern recognition , 2019, Evol. Intell..

[7]  W. Gerstner,et al.  The temporal paradox of Hebbian learning and homeostatic plasticity , 2017, Current Opinion in Neurobiology.

[8]  Alexander Gepperth,et al.  A Bio-Inspired Incremental Learning Architecture for Applied Perceptual Problems , 2016, Cognitive Computation.

[9]  Priyadarshini Panda,et al.  Tree-CNN: A hierarchical Deep Convolutional Neural Network for incremental learning , 2018, Neural Networks.

[10]  Jong-Hwan Kim,et al.  Incremental Class Learning for Hierarchical Classification , 2020, IEEE Transactions on Cybernetics.

[11]  Weiming Dong,et al.  Incremental Concept Learning via Online Generative Memory Recall , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Nicolas Y. Masse,et al.  Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization , 2018, Proceedings of the National Academy of Sciences.

[13]  Wendong Xiao,et al.  Non-iterative and Fast Deep Learning: Multilayer Extreme Learning Machines , 2020, J. Frankl. Inst..

[14]  James L. McClelland,et al.  Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. , 1995, Psychological review.

[15]  Xinying Xu,et al.  Exemplar-Supported Representation for Effective Class-Incremental Learning , 2020, IEEE Access.

[16]  Chunlin Chen,et al.  Incremental Reinforcement Learning in Continuous Spaces via Policy Relaxation and Importance Weighting , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[17]  L. Abbott,et al.  Competitive Hebbian learning through spike-timing-dependent synaptic plasticity , 2000, Nature Neuroscience.

[18]  Rodrigo Salas,et al.  Self-Improving Generative Artificial Neural Network for Pseudorehearsal Incremental Class Learning , 2019, Algorithms.

[19]  Nasser L. Azad,et al.  A robust safety-oriented autonomous cruise control scheme for electric vehicles based on model predictive control and online sequential extreme learning machine with a hyper-level fault tolerance-based supervisor , 2015, Neurocomputing.

[20]  Anthony V. Robins,et al.  Catastrophic Forgetting, Rehearsal and Pseudorehearsal , 1995, Connect. Sci..

[21]  Peng Li,et al.  An Incremental Deep Convolutional Computation Model for Feature Learning on Industrial Big Data , 2019, IEEE Transactions on Industrial Informatics.

[22]  Shiliang Pu,et al.  IROS 2019 Lifelong Robotic Vision: Object Recognition Challenge [Competitions] , 2020, IEEE Robotics Autom. Mag..

[23]  Jaya Krishna Mandivarapu,et al.  Self-Net: Lifelong Learning via Continual Self-Modeling , 2018, Frontiers in Artificial Intelligence.

[24]  Kaushik Roy,et al.  Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing , 2017, IEEE Access.

[25]  Hongzhi Wang,et al.  Life-long learning based on dynamic combination model , 2017, Appl. Soft Comput..

[26]  L. Abbott,et al.  Synaptic plasticity: taming the beast , 2000, Nature Neuroscience.

[27]  Vasant Honavar,et al.  Learn++: an incremental learning algorithm for supervised neural networks , 2001, IEEE Trans. Syst. Man Cybern. Part C.

[28]  Davide Maltoni,et al.  Continuous Learning in Single-Incremental-Task Scenarios , 2018, Neural Networks.

[29]  Labiba Souici-Meslati,et al.  A Novel Incremental Learning Algorithm Based on Incremental Support Vector Machina and Incremental Neural Network Learn++ , 2019, Rev. d'Intelligence Artif..

[30]  Xiaohui Peng,et al.  A novel random forests based class incremental learning method for activity recognition , 2018, Pattern Recognit..

[31]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[32]  W. Abraham,et al.  Memory retention – the synaptic stability versus plasticity dilemma , 2005, Trends in Neurosciences.

[33]  Jaihie Kim,et al.  An incremental learning method for spoof fingerprint detection , 2019, Expert Syst. Appl..

[34]  Jonathan D. Power,et al.  Neural plasticity across the lifespan , 2017, Wiley interdisciplinary reviews. Developmental biology.

[35]  Itamar Arel,et al.  This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 1 Ensemble Learning in Fixed Expansion Layer Network , 2022 .

[36]  Yun Xiang,et al.  Efficient Incremental Learning Using Dynamic Correction Vector , 2020, IEEE Access.

[37]  Rosa H. M. Chan,et al.  Challenges in Task Incremental Learning for Assistive Robotics , 2020, IEEE Access.

[38]  Heiko Wersing,et al.  Incremental on-line learning: A review and comparison of state of the art algorithms , 2018, Neurocomputing.

[39]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .