Can Sequential Bayesian Inference Solve Continual Learning?
Previous work in Continual Learning (CL) has used sequential Bayesian inference to prevent forgetting and accumulate knowledge from previous tasks. A limiting factor to performing Bayesian CL has been exact inference in a Bayesian Neural Network (NN). We perform sequential Bayesian inference with a Bayesian NN using Hamiltonian Monte Carlo (HMC) and propagate the posterior as a prior for a new task by fitting a density estimator on HMC samples. We find that this approach fails to prevent forgetting. We propose an alternative view of the CL problem which directly models the data generating process and decomposes the CL problem in task specific and shared parameters. This method named Prototypical Bayesian CL and performs well compared to the latest Bayesian CL methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceContinual LearningSequential Bayesian InferenceSimilar Papers 제목 키워드 기반
On Sequential Bayesian Inference for Continual Learning
Sequential Bayesian inference can be used for continual learning to prevent catastrophic forgetting of past tasks and provide an informative prior when learning new tasks. We revisit sequential Bayesian inference and tes…
Bayesian InferenceContinual LearningSequential Bayesian InferenceVariational Auto-Regressive Gaussian Processes for Continual Learning
Through sequential construction of posteriors on observing data online, Bayes' theorem provides a natural framework for continual learning. We develop Variational Auto-Regressive Gaussian Processes (VAR-GPs), a principle…
Bayesian InferenceContinual LearningGaussian ProcessesThe Bayesian Approach to Continual Learning: An Overview
Continual learning is an online paradigm where a learner continually accumulates knowledge from different tasks encountered over sequential time steps. Importantly, the learner is required to extend and update its knowle…
Bayesian Inferenceclass-incremental learningClass Incremental LearningContinual Learning+4Continual Learning via Sequential Function-Space Variational Inference
Sequential Bayesian inference over predictive functions is a natural framework for continual learning from streams of data. However, applying it to neural networks has proved challenging in practice. Addressing the drawb…
Bayesian InferenceContinual LearningSequential Bayesian InferenceVariational InferenceFacilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients
Continual learning aims to enable machine learning models to learn a general solution space for past and future tasks in a sequential manner. Conventional models tend to forget the knowledge of previous tasks while learn…
Continual LearningTask 2