Instead of considering "online" and "continual" learning as inconvenient constraints to avoid, in

We thank all of the reviewers for their time, effort and engagement with our work. A concrete example of this is the "Gaussian Gated Linear Networks" paper (which can ImageNet), but it's worth noting that (1) the two fields are solving very different problems, and (2) that even Thank you for all the helpful suggestions, they are well taken. This is a misunderstanding so we thank the reviewer for raising it. We will clarify and emphasize this critical point in text. Why is the method not compared to the original GLN?

Instead of considering "online" and "continual" learning as inconvenient constraints to avoid, in

Human intelligence is characterized not only by the capacity to learn complex skills, but the ability to rapidly adapt and acquire new skills within an ever-changing environment. In this work we study how the learning of modular solutions can allow for effective generalization to both unseen and potentially differently distributed data. Our main postulate is that the combination of task segmentation, modular learning and memory-based ensembling can give rise to generalization on an exponentially growing number of unseen tasks. We provide a concrete instantiation of this idea using a combination of: (1) the Forget-Me-Not Process, for task segmentation and memory based ensembling; and (2) Gated Linear Networks, which in contrast to contemporary deep learning techniques use a modular and local learning mechanism. We demonstrate that this system exhibits a number of desirable continual learning properties: robustness to catastrophic forgetting, no negative transfer and increasing levels of positive transfer as more tasks are seen. We show competitive performance against both offline and online methods on standard continual learning benchmarks.