Continual Learning using the SHDL Framework with Skewed Replay Distributions
Human and animals continuously acquire, adapt as well as transfer knowledge throughout their lifespan. The ability to learn continuously is crucial for the effective functioning of agents interacting with the real world and processing continuous streams of information. Continuous learning has been a long-standing challenge for neural networks as the repeated acquisition of information from non-uniform data distributions generally lead to catastrophic forgetting or interference. This work proposes a modular architecture capable of continuous acquisition of tasks while averting catastrophic forgetting. Specifically, our contributions are: (i) Efficient Architecture: a modular architecture emulating the visual cortex that can learn meaningful representations with limited labelled examples, (ii) Knowledge Retention: retention of learned knowledge via limited replay of past experiences, (iii) Forward Transfer: efficient and relatively faster learning on new tasks, and (iv) Naturally Skewed Distributions: The learning in the above-mentioned claims is performed on non-uniform data distributions which better represent the natural statistics of our ongoing experience. Several experiments that substantiate the above-mentioned claims are demonstrated on the CIFAR-100 dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningSimilar Papers 제목 키워드 기반
ScatterNet Hybrid Deep Learning (SHDL) Network For Object Classification
The paper proposes the ScatterNet Hybrid Deep Learning (SHDL) network that extracts invariant and discriminative image representations for object recognition. SHDL framework is constructed with a multi-layer ScatterNet f…
ClassificationDeep LearningGeneral ClassificationObject+1Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay
We study continual offline reinforcement learning, a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks. We propose a dual generative replay fram…
Continual Learningreinforcement-learningReinforcement LearningGenerative ScatterNet Hybrid Deep Learning (G-SHDL) Network with Structural Priors for Semantic Image Segmentation
This paper proposes a generative ScatterNet hybrid deep learning (G-SHDL) network for semantic image segmentation. The proposed generative architecture is able to train rapidly from relatively small labeled datasets usin…
General ClassificationImage SegmentationSemantic SegmentationTeaching AI to Remember: Insights from Brain-Inspired Replay in Continual Learning
Artificial neural networks (ANNs) continue to face challenges in continual learning, particularly due to catastrophic forgetting, the loss of previously learned knowledge when acquiring new tasks. Inspired by memory cons…
Continual LearningAttention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs
Multimodal large language models (MLLMs) are increasingly required to adapt to non-stationary streams of visual domains, question types, and user instructions, yet continual fine-tuning often causes severe forgetting of …
Continual Learning