标题： 基于混合生物启发学习规则的神经架构搜索 显示英文标题

标题： Neural Architecture Search with Mixed Bio-inspired Learning Rules

摘要： 生物启发神经网络因其对抗鲁棒性、能耗节约以及更贴近皮层生理学而受到关注，但它们在准确性和可扩展性方面通常落后于基于反向传播（BP）的模型。 我们表明，允许在不同层中使用不同的生物启发学习规则，并通过定制的神经架构搜索（NAS）过程自动发现这些规则，可以弥补这一差距。 从标准的NAS基线开始，我们扩大了搜索空间，以包括生物启发学习规则，并使用NAS来找到每层最佳的架构和学习规则。 我们证明，为不同层使用不同的生物启发学习规则的神经网络比在整个层中使用单一规则的网络具有更好的准确性。 所得到的使用多种生物启发学习规则的神经网络为生物启发模型设定了新纪录：在CIFAR-10上达到95.16%，在CIFAR-100上达到76.48%，在ImageNet16-120上达到43.42%，在ImageNet上的top-1得分为60.51%。 在某些情况下，它们甚至超越了相应的基于BP的网络，同时保留了其鲁棒性的优势。 我们的结果表明，学习规则的分层多样性可以实现更好的可扩展性和准确性，并促使进一步研究在同一网络中混合多种生物启发学习规则。 显示英文摘要

摘要： Bio-inspired neural networks are attractive for their adversarial robustness, energy frugality, and closer alignment with cortical physiology, yet they often lag behind back-propagation (BP) based models in accuracy and ability to scale. We show that allowing the use of different bio-inspired learning rules in different layers, discovered automatically by a tailored neural-architecture-search (NAS) procedure, bridges this gap. Starting from standard NAS baselines, we enlarge the search space to include bio-inspired learning rules and use NAS to find the best architecture and learning rule to use in each layer. We show that neural networks that use different bio-inspired learning rules for different layers have better accuracy than those that use a single rule across all the layers. The resulting NN that uses a mix of bio-inspired learning rules sets new records for bio-inspired models: 95.16% on CIFAR-10, 76.48% on CIFAR-100, 43.42% on ImageNet16-120, and 60.51% top-1 on ImageNet. In some regimes, they even surpass comparable BP-based networks while retaining their robustness advantages. Our results suggest that layer-wise diversity in learning rules allows better scalability and accuracy, and motivates further research on mixing multiple bio-inspired learning rules in the same network.