REMIND Your Neural Network to Prevent Catastrophic Forgetting
REMIND Your Neural Network to Prevent Catastrophic Forgetting
复制标题
DOI：
10.1007/978-3-030-58598-3_28
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Tyler L. Hayes;Kushal Kafle;Robik Shrestha;Manoj Acharya;Christopher Kanan
中科院分区：
文献类型：
--
作者：
Tyler L. Hayes;Kushal Kafle;Robik Shrestha;Manoj Acharya;Christopher Kanan
人们一生都在学习。然而，增量更新传统神经网络会导致灾难性的遗忘。一种常见的补救方法是重放，这是受到大脑如何巩固记忆的启发。重播涉及在新旧实例的混合上微调网络。虽然有神经科学证据表明大脑会重放压缩的记忆，但卷积网络的现有方法会重放原始图像。在这里，我们提出了REMIND，这是一种受大脑启发的方法，可以使用压缩表示进行高效重放。REMIND是以在线方式训练的，这意味着它一次学习一个例子，这更接近人类的学习方式。在相同的约束条件下，REMIND在ImageNet ILSVRC-2012数据集上的增量类学习性能优于其他方法。我们探测REMIND的鲁棒性已知的数据排序方案，引起灾难性的遗忘。我们展示了REMIND的通用性，通过开创性的在线学习视觉问答（VQA）（ https://github.com/tyler-hayes/REMIND ).
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) ( https://github.com/tyler-hayes/REMIND ).