REMIND Your Neural Network to Prevent Catastrophic Forgetting
This addresses the issue of enabling neural networks to learn continuously without forgetting, which is crucial for applications requiring lifelong learning, though it is incremental in nature.
The paper tackles the problem of catastrophic forgetting in neural networks by proposing REMIND, a brain-inspired approach that uses compressed representations for efficient replay, achieving superior performance on incremental class learning with ImageNet ILSVRC-2012 under the same constraints.
People learn throughout life. However, incrementally updating conventional neural networks leads to catastrophic forgetting. A common remedy is replay, which is inspired by how the brain consolidates memory. Replay involves fine-tuning a network on a mixture of new and old instances. While there is neuroscientific evidence that the brain replays compressed memories, existing methods for convolutional networks replay raw images. Here, we propose REMIND, a brain-inspired approach that enables efficient replay with compressed representations. REMIND is trained in an online manner, meaning it learns one example at a time, which is closer to how humans learn. Under the same constraints, REMIND outperforms other methods for incremental class learning on the ImageNet ILSVRC-2012 dataset. We probe REMIND's robustness to data ordering schemes known to induce catastrophic forgetting. We demonstrate REMIND's generality by pioneering online learning for Visual Question Answering (VQA).