paper-with-me

홈 › Papers

Continual Learning using the SHDL Framework with Skewed Replay Distributions

2019-09-25 · Amarjot Singh, Jay McClelland

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

ScatterNet Hybrid Deep Learning (SHDL) Network For Object Classification

2017-08-30 · Amarjot Singh, Nick Kingsbury

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+1

Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay

2024-04-16 · Jinmei Liu, Wenbin Li, Xiangyu Yue, Shilin Zhang 외

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 Learning

Generative ScatterNet Hybrid Deep Learning (G-SHDL) Network with Structural Priors for Semantic Image Segmentation

2018-02-09 · Amarjot Singh, Nick Kingsbury

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 Segmentation

Teaching AI to Remember: Insights from Brain-Inspired Replay in Continual Learning

2025-08-24 · Jina Kim arxiv

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 Learning

Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs

2026-06-22 · Chuangxin Zhao, Canran Xiao, Siyuan Ma, Mengyao Lyu 외 arxiv

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