Reconciling meta-learning and continual learning with online mixtures of tasks
원문 초록
Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task. This approach encounters difficulty when transfer is not advantageous, for instance, when tasks are considerably dissimilar or change over time. We use the connection between gradient-based meta-learning and hierarchical Bayes to propose a Dirichlet process mixture of hierarchical Bayesian models over the parameters of an arbitrary parametric model such as a neural network. In contrast to consolidating inductive biases into a single set of hyperparameters, our approach of task-dependent hyperparameter selection better handles latent distribution shift, as demonstrated on a set of evolving, image-based, few-shot learning benchmarks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Fuzzy Graph Neural Network for Few-Shot Learning
Chameleon: A MatMul-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data
The Bayesian Approach to Continual Learning: An Overview
Few-Shot Learning for Industrial Time Series: A Comparative Analysis Using the Example of Screw-Fastening Process Monitoring
Hyperbolic Dual Feature Augmentation for Open-Environment
The Hippocampal Place Field Gradient: An Eigenmode Theory Linking Grid Cell Projections to Multiscale Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.