Despite the progress in deep learning networks, efficient learning at the edge (enabling adaptable, low-complexity machine learning solutions) remains a critical need for defense and commercial applications. We envision a pipeline to utilize large neuroimaging datasets, including maps of the brain which capture neuron and synapse connectivity, to improve machine learning approaches. We have pursued different approaches within this pipeline structure. First, as a demonstration of data-driven discovery, the team has developed a technique for discovery of repeated subcircuits, or motifs. These were incorporated into a neural architecture search approach to evolve network architectures. Second, we have conducted analysis of the heading direction circuit in the fruit fly, which performs fusion of visual and angular velocity features, to explore augmenting existing computational models with new insight. Our team discovered a novel pattern of connectivity, implemented a new model, and demonstrated sensor fusion on a robotic platform. Third, the team analyzed circuitry for memory formation in the fruit fly connectome, enabling the design of a novel generative replay approach. Finally, the team has begun analysis of connectivity in mammalian cortex to explore potential improvements to transformer networks. These constraints increased network robustness on the most challenging examples in the CIFAR-10-C computer vision robustness benchmark task, while reducing learnable attention parameters by over an order of magnitude. Taken together, these results demonstrate multiple potential approaches to utilize insight from neural systems for developing robust and efficient machine learning techniques.

翻译：尽管深度学习网络取得了进展，但边缘端的高效学习（实现自适应、低复杂度的机器学习解决方案）仍是国防和商业应用的关键需求。我们设想构建一条利用大规模神经影像数据集（包括捕捉神经元和突触连接模式的脑图谱）来改进机器学习方法的流水线。在该流水线架构中，我们探索了不同路径。首先，作为数据驱动发现的示范，团队开发了重复子回路（即基模）的发现技术，并将其融入神经架构搜索方法中以演化网络架构。其次，通过分析果蝇头部朝向回路（该回路融合视觉和角速度特征），我们探索了用新见解增强现有计算模型的方法。团队发现了新型连接模式，实现了新模型，并在机器人平台上演示了传感器融合。第三，团队解析了果蝇连接组中记忆形成的神经回路，从而设计出新型生成式重放方法。最后，团队开始分析哺乳动物皮层连接性，以探索改进Transformer网络的潜在方案。这些约束在CIFAR-10-C计算机视觉鲁棒性基准任务的最具挑战性样本上提升了网络鲁棒性，同时将可学习注意力参数减少了一个数量级以上。综上，这些成果展示了利用神经系统洞察开发稳健高效机器学习技术的多种可行路径。