paper-with-me

홈 › Papers

Continual Learning with Fully Probabilistic Models

2021-04-19 · Benedikt Pfülb, Alexander Gepperth, Benedikt Bagus

We present an approach for continual learning (CL) that is based on fully probabilistic (or generative) models of machine learning. In contrast to, e.g., GANs that are "generative" in the sense that they can generate samples, fully probabilistic models aim at modeling the data distribution directly. Consequently, they provide functionalities that are highly relevant for continual learning, such as density estimation (outlier detection) and sample generation. As a concrete realization of generative continual learning, we propose Gaussian Mixture Replay (GMR). GMR is a pseudo-rehearsal approach using a Gaussian Mixture Model (GMM) instance for both generator and classifier functionalities. Relying on the MNIST, FashionMNIST and Devanagari benchmarks, we first demonstrate unsupervised task boundary detection by GMM density estimation, which we also use to reject untypical generated samples. In addition, we show that GMR is capable of class-conditional sampling in the way of a cGAN. Lastly, we verify that GMR, despite its simple structure, achieves state-of-the-art performance on common class-incremental learning problems at very competitive time and memory complexity.

📄 PDF Abstract BibTeX arXiv:2104.09240

Code (0)

등록된 구현이 없습니다.

Tasks

Boundary Detectionclass-incremental learningClass Incremental LearningContinual LearningDensity EstimationIncremental LearningOutlier Detection

Similar Papers 제목 키워드 기반

Probabilistic Metaplasticity for Continual Learning with Memristors

2024-03-13 · Fatima Tuz Zohora, Vedant Karia, Nicholas Soures, Dhireesha Kudithipudi

Edge devices operating in dynamic environments critically need the ability to continually learn without catastrophic forgetting. The strict resource constraints in these devices pose a major challenge to achieve this, as…

Continual Learning

Continual Learning with Adaptive Weights (CLAW)

2019-11-21 · ICLR 2020 1 · Tameem Adel, Han Zhao, Richard E. Turner

Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner. Recently, several frameworks have been developed which enable deep learning to be deployed in this learni…

Continual LearningTransfer LearningVariational Inference

Learning Probabilistic Prompt for Continual Learning

2026-07-06 · Hyekang Park, Sanghoon Lee, Geon Lee, Jongyoun Noh 외 arxiv

Continual learning aims to progressively learn from a sequence of tasks, each containing a disjoint subset of classes, while preserving previously learned knowledge. Prompt-based continual learning methods propose to lea…

Continual Learning

Variational Continual Learning

2017-10-29 · ICLR 2018 1 · Cuong V. Nguyen, Yingzhen Li, Thang D. Bui, Richard E. Turner

This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The …

Continual LearningVariational Inference

Posterior Meta-Replay for Continual Learning

2021-03-01 · NeurIPS 2021 12 · Christian Henning, Maria R. Cervera, Francesco D'Angelo, Johannes von Oswald 외

Learning a sequence of tasks without access to i.i.d. observations is a widely studied form of continual learning (CL) that remains challenging. In principle, Bayesian learning directly applies to this setting, since rec…

Continual Learning