动态Sensorium竞赛回顾：基于视频预测小鼠初级视觉皮层大规模活动
Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos
AI总结：
本研究设立Sensorium 2023动态视觉系统预测基准竞赛，基于10只小鼠初级视觉皮层的大规模神经元数据集，分两个赛道评估模型性能，推动了小鼠视觉系统动态预测模型的发展，获胜模型较此前最优水平提升50%。
摘要：
由于视觉输入与神经元反应之间存在非线性关系，理解生物视觉系统如何处理信息是一项具有挑战性的课题。人工神经网络为计算神经科学家提供了构建连接生物视觉与机器视觉的预测模型的途径。机器学习领域的发展极大受益于各类基准测试，这类测试可在标准化条件下针对同一任务比较不同模型的表现。然而，目前尚无用于确定小鼠视觉系统最优动态模型的标准化基准。为填补这一空白，我们设立了带有动态输入的Sensorium 2023基准竞赛，该竞赛采用了一个全新的大规模数据集，数据来自10只小鼠的初级视觉皮层。该数据集包含78853个神经元的反应数据，每个神经元对应2小时的动态刺激反应，同时还包含跑动速度、瞳孔扩张和眼球运动等行为测量数据。竞赛根据模型在留出测试集上的神经元反应预测性能，分两个赛道对模型进行排名：一个赛道聚焦于域内自然刺激的预测，另一个赛道则针对分布外（OOD）刺激以评估模型的泛化能力。作为NeurIPS 2023竞赛赛道的一部分，我们收到了来自22支团队的160多份模型提交作品。参赛团队提出了多种新型预测模型架构，获胜团队的表现较此前的最优模型提升了50%。该数据集及基准测试基础设施将继续在www.sensorium-competition.net网站上开放获取。
英文摘要：
Understanding how biological visual systems process information is challenging because of the nonlinear relationship between visual input and neuronal responses. Artificial neural networks allow computational neuroscientists to create predictive models that connect biological and machine vision. Machine learning has benefited tremendously from benchmarks that compare different model on the same task under standardized conditions. However, there was no standardized benchmark to identify state-of-the-art dynamic models of the mouse visual system. To address this gap, we established the Sensorium 2023 Benchmark Competition with dynamic input, featuring a new large-scale dataset from the primary visual cortex of ten mice. This dataset includes responses from 78,853 neurons to 2 hours of dynamic stimuli per neuron, together with the behavioral measurements such as running speed, pupil dilation, and eye movements. The competition ranked models in two tracks based on predictive performance for neuronal responses on a held-out test set: one focusing on predicting in-domain natural stimuli and another on out-of-distribution (OOD) stimuli to assess model generalization. As part of the NeurIPS 2023 competition track, we received more than 160 model submissions from 22 teams. Several new architectures for predictive models were proposed, and the winning teams improved the previous state-of-the-art model by 50%. Access to the dataset as well as the benchmarking infrastructure will remain online at www.sensorium-competition.net.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
