Continual Classification Learning Using Generative Models
This work addresses the problem of catastrophic forgetting in neural networks for researchers in continual learning, but it appears incremental as it extends prior generative methods to classification.
The paper tackles catastrophic forgetting in continual learning by proposing a classification model that learns sequentially from tasks while retaining previous knowledge, building on existing generative capabilities and deriving a new variational bound for joint likelihood.
Continual learning is the ability to sequentially learn over time by accommodating knowledge while retaining previously learned experiences. Neural networks can learn multiple tasks when trained on them jointly, but cannot maintain performance on previously learned tasks when tasks are presented one at a time. This problem is called catastrophic forgetting. In this work, we propose a classification model that learns continuously from sequentially observed tasks, while preventing catastrophic forgetting. We build on the lifelong generative capabilities of [10] and extend it to the classification setting by deriving a new variational bound on the joint log likelihood, $\log p(x; y)$.