Zhang Wenli, Wang Yaoyuan, Ji Xinglong, Wu Yujie, Zhao Rong
Department of Precision Instrument, Center for Brain Inspired Computing Research, Beijing Innovation Center for Future Chip, Tsinghua University, Beijing, China.
Front Artif Intell. 2021 Oct 15;4:692065. doi: 10.3389/frai.2021.692065. eCollection 2021.
Memristors show great promise in neuromorphic computing owing to their high-density integration, fast computing and low-energy consumption. However, the non-ideal update of synaptic weight in memristor devices, including nonlinearity, asymmetry and device variation, still poses challenges to the learning of memristors, thereby limiting their broad applications. Although the existing offline learning schemes can avoid this problem by transferring the weight optimization process into cloud, it is difficult to adapt to unseen tasks and uncertain environments. Here, we propose a bi-level meta-learning scheme that can alleviate the non-ideal update problem, and achieve fast adaptation and high accuracy, named Rapid One-step Adaption (ROA). By introducing a special regularization constraint and a dynamic learning rate strategy for learning, the ROA method effectively combines offline pre-training and online rapid one-step adaption. Furthermore, we implemented it on memristor-based neural networks to solve few-shot learning tasks, proving its superiority over the pure offline and online schemes under noisy conditions. This method can solve learning in non-ideal memristor networks, providing potential applications of on-chip neuromorphic learning and edge computing.
忆阻器因其高密度集成、快速计算和低能耗，在神经形态计算领域展现出巨大潜力。然而，忆阻器器件中突触权重的非理想更新，包括非线性、不对称性和器件变化，仍然给忆阻器的学习带来挑战，从而限制了它们的广泛应用。尽管现有的离线学习方案可以通过将权重优化过程转移到云端来避免这个问题，但它难以适应未见任务和不确定环境。在此，我们提出一种双层元学习方案，该方案可以缓解非理想更新问题，并实现快速适应和高精度，名为快速一步适应（ROA）。通过引入特殊的正则化约束和用于学习的动态学习率策略，ROA方法有效地结合了离线预训练和在线快速一步适应。此外，我们在基于忆阻器的神经网络上实现了该方法，以解决少样本学习任务，证明了其在噪声条件下优于纯离线和在线方案。该方法可以解决非理想忆阻器网络中的学习问题，为片上神经形态学习和边缘计算提供了潜在应用。
