Tanaka Hidenori, Nayebi Aran, Maheswaranathan Niru, McIntosh Lane, Baccus Stephen A, Ganguli Surya
Physics & Informatics Laboratories, NTT Research, Inc., East Palo Alto, CA, USA.
Department of Applied Physics, Stanford University, Stanford, CA, USA.
Adv Neural Inf Process Syst. 2019 Dec;32:8537-8547.
Recently, deep feedforward neural networks have achieved considerable success in modeling biological sensory processing, in terms of reproducing the input-output map of sensory neurons. However, such models raise profound questions about the very nature of explanation in neuroscience. Are we simply replacing one complex system (a biological circuit) with another (a deep network), without understanding either? Moreover, beyond neural representations, are the deep network's for generating neural responses the same as those in the brain? Without a systematic approach to extracting and understanding computational mechanisms from deep neural network models, it can be difficult both to assess the degree of utility of deep learning approaches in neuroscience, and to extract experimentally testable hypotheses from deep networks. We develop such a systematic approach by combining dimensionality reduction and modern attribution methods for determining the relative importance of interneurons for specific visual computations. We apply this approach to deep network models of the retina, revealing a conceptual understanding of how the retina acts as a predictive feature extractor that signals deviations from expectations for diverse spatiotemporal stimuli. For each stimulus, our extracted computational mechanisms are consistent with prior scientific literature, and in one case yields a new mechanistic hypothesis. Thus overall, this work not only yields insights into the computational mechanisms underlying the striking predictive capabilities of the retina, but also places the framework of deep networks as neuroscientific models on firmer theoretical foundations, by providing a new roadmap to go beyond comparing neural representations to extracting and understand computational mechanisms.
最近，深度前馈神经网络在对生物感官处理进行建模方面取得了显著成功，即在再现感觉神经元的输入-输出映射方面。然而，这类模型引发了关于神经科学中解释本质的深刻问题。我们是否只是用另一个复杂系统（深度网络）取代了一个（生物回路），而对两者都没有理解？此外，除了神经表征之外，深度网络生成神经反应的机制与大脑中的机制相同吗？如果没有一种系统的方法来从深度神经网络模型中提取和理解计算机制，就很难评估深度学习方法在神经科学中的实用程度，也很难从深度网络中提取可通过实验检验的假设。我们通过结合降维和现代归因方法来开发这样一种系统方法，以确定中间神经元对特定视觉计算的相对重要性。我们将这种方法应用于视网膜的深度网络模型，揭示了对视网膜如何作为一个预测性特征提取器的概念性理解，该提取器能够发出与对各种时空刺激的预期偏差的信号。对于每种刺激，我们提取的计算机制与先前的科学文献一致，并且在一个案例中产生了一个新的机制假设。因此，总体而言，这项工作不仅深入了解了视网膜惊人预测能力背后的计算机制，还通过提供一个超越比较神经表征以提取和理解计算机制的新路线图，将深度网络作为神经科学模型的框架置于更坚实的理论基础之上。
