Uncertainty-based Continual Learning with Adaptive Regularization

by   Hongjoon Ahn, et al.

We introduce a new regularization-based continual learning algorithm, dubbed as Uncertainty-regularized Continual Learning (UCL), that stores much smaller number of additional parameters for regularization terms than the recent state-of-the-art methods. Our approach builds upon the Bayesian learning framework, but makes a fresh interpretation of the variational approximation based regularization term and defines a notion of "uncertainty" for each hidden node in the network. The regularization parameter of each weight is then set to be large when the uncertainty of either of the node that the weight connects is small, since the weights connected to an important node should be less updated when a new task comes. Moreover, we add two additional regularization terms; one that promotes freezing the weights that are identified to be important (i.e., certain) for past tasks, and the other that gives flexibility to control the actively learning parameters for a new task by gracefully forgetting what was learned before. In results, we show our UCL outperforms most of recent state-of-the-art baselines on both supervised learning and reinforcement learning benchmarks.


page 1

page 2

page 3

page 4


Adaptive Group Sparse Regularization for Continual Learning

We propose a novel regularization-based continual learning method, dubbe...

Uncertainty-guided Continual Learning with Bayesian Neural Networks

Continual learning aims to learn new tasks without forgetting previously...

Self-paced Weight Consolidation for Continual Learning

Continual learning algorithms which keep the parameters of new tasks clo...

Fixed Design Analysis of Regularization-Based Continual Learning

We consider a continual learning (CL) problem with two linear regression...

Regularization-based Continual Learning for Fault Prediction in Lithium-Ion Batteries

In recent years, the use of lithium-ion batteries has greatly expanded i...

ScrollNet: Dynamic Weight Importance for Continual Learning

The principle underlying most existing continual learning (CL) methods i...

Continual learning with direction-constrained optimization

This paper studies a new design of the optimization algorithm for traini...

Please sign up or login with your details

Forgot password? Click here to reset