Unlike the brain, artificial neural networks, including state-of-the-art deep neural networks for computer vision, are subject to "catastrophic forgetting": they rapidly forget the previous task when trained on a new one. Neuroscience suggests that biological synapses avoid this issue through the process of synaptic consolidation and metaplasticity: the plasticity itself changes upon repeated synaptic events. In this work, we show that this concept of metaplasticity can be transferred to a particular type of deep neural networks, binarized neural networks, to reduce catastrophic forgetting.

中文翻译：

---

二值神经网络的突触可塑性

与大脑不同，人工神经网络（包括用于计算机视觉的最先进的深度神经网络）容易遭受“灾难性的遗忘”：在接受新的训练时，它们会迅速忘记先前的任务。神经科学表明，生物突触可通过突触巩固和可塑化过程避免此问题：可塑性本身在重复的突触事件后会发生变化。在这项工作中，我们证明了这种可塑性的概念可以转移到特定类型的深层神经网络，即二值化神经网络，以减少灾难性的遗忘。