paper-with-me

Papers

Continual Deep Learning by Functional Regularisation of Memorable Past

2020-04-29 · NeurIPS 2020 12 · Pingbo Pan, Siddharth Swaroop, Alexander Immer, Runa Eschenhagen, Richard E. Turner, Mohammad Emtiyaz Khan

Continually learning new skills is important for intelligent systems, yet standard deep learning methods suffer from catastrophic forgetting of the past. Recent works address this with weight regularisation. Functional regularisation, although computationally expensive, is expected to perform better, but rarely does so in practice. In this paper, we fix this issue by using a new functional-regularisation approach that utilises a few memorable past examples crucial to avoid forgetting. By using a Gaussian Process formulation of deep networks, our approach enables training in weight-space while identifying both the memorable past and a functional prior. Our method achieves state-of-the-art performance on standard benchmarks and opens a new direction for life-long learning where regularisation and memory-based methods are naturally combined.

📄 PDF Abstract BibTeX arXiv:2004.14070

Code (1)

team-approx-bayes/fromp 공식 구현 pytorch

Tasks

Deep Learning

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

Monte Carlo Functional Regularisation for Continual Learning

2025-08-18 · Pengcheng Hao, Menghao Waiyan William Zhu, Ercan Engin Kuruoglu arxiv

Continual learning (CL) is crucial for the adaptation of neural network models to new environments. Although outperforming weight-space regularisation approaches, the functional regularisation-based CL methods suffer fro…

Continual Learning

Functional Regularisation for Continual Learning with Gaussian Processes

2019-01-31 · ICLR 2020 1 · Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu 외

We introduce a framework for Continual Learning (CL) based on Bayesian inference over the function space rather than the parameters of a deep neural network. This method, referred to as functional regularisation for Cont…

Bayesian InferenceContinual LearningGaussian ProcessesSequential Bayesian Inference

Affect and Effect: Limitations of regularisation-based continual learning in EEG-based emotion classification

2026-01-09 · Nina Peire, Yupei Li, Björn Schuller arxiv

Generalisation to unseen subjects in EEG-based emotion classification remains a challenge due to high inter-and intra-subject variability. Continual learning (CL) poses a promising solution by learning from a sequence of…

Emotion ClassificationContinual Learning

Continual learning via probabilistic exchangeable sequence modelling

2025-03-26 · Hanwen Xing, Christopher Yau

Continual learning (CL) refers to the ability to continuously learn and accumulate new knowledge while retaining useful information from past experiences. Although numerous CL methods have been proposed in recent years, …

class-incremental learningClass Incremental LearningContinual LearningDecision Making+2

A Framework of Meta Functional Learning for Regularising Knowledge Transfer

2022-03-28 · Pan Li, Yanwei Fu, Shaogang Gong

Machine learning classifiers' capability is largely dependent on the scale of available training data and limited by the model overfitting in data-scarce learning tasks. To address this problem, this work proposes a nove…

Cross-Domain Few-Shotcross-domain few-shot learningFew-Shot LearningMeta-Learning+1