Biological connectomes as a representation for the Architecture of Artificial Neural Networks
Biological connectomes as a representation for the Architecture of Artificial Neural Networks
复制标题
生物连接组作为人工神经网络架构的代表
DOI：
10.1101/2022.09.30.510374
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Maryam Parsa
中科院分区：
文献类型：
--
作者：
Samuel Schmidgall;Catherine D. Schuman;Maryam Parsa
神经科学的重大努力正在绘制许多新物种的连接图，包括即将完成的果蝇黑腹果蝇。重要的是要问一问，这些模型是否会让人工智能受益。在这项工作中，我们问了两个基本问题：(1)生物连接体在哪里以及何时可以在机器学习中提供使用；(2)为了提取良好的连接体表示，哪些设计原则是必要的。为此，我们将线虫线虫的运动电路翻译成不同生物物理实在论水平的人工神经网络，并评估这些网络在运动和非运动行为任务上的训练结果。我们论证了不需要坚持生物物理实在论就能获得使用生物回路的优势。我们还确定，即使没有保留确切的接线图，架构统计数据也提供了有价值的先验信息。最后，我们发现，虽然线虫的运动回路在运动问题上提供了强大的感应偏向，但其结构可能会阻碍与运动无关的任务的执行，如视觉分类问题。
Grand efforts in neuroscience are working toward mapping the connectomes of many new species, including the near completion of the Drosophila melanogaster. It is important to ask whether these models could benefit artificial intelligence. In this work we ask two fundamental questions: (1) where and when biological connectomes can provide use in machine learning, (2) which design principles are necessary for extracting a good representation of the connectome. Toward this end, we translate the motor circuit of the C. Elegans nematode into artificial neural networks at varying levels of biophysical realism and evaluate the outcome of training these networks on motor and non-motor behavioral tasks. We demonstrate that biophysical realism need not be upheld to attain the advantages of using biological circuits. We also establish that, even if the exact wiring diagram is not retained, the architectural statistics provide a valuable prior. Finally, we show that while the C. Elegans locomotion circuit provides a powerful inductive bias on locomotion problems, its structure may hinder performance on tasks unrelated to locomotion such as visual classification problems.