[论文解读] From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction

Hidenori Tanaka, Aran Nayebi+4 more|arXiv (Cornell University)|Dec 12, 2019

Neural dynamics and brain function被引用 42

一句话总结

本论文开发了一个系统的模型简化工作流，从深度CNN模型的视网膜中提取机制子网络，为预测性视网膜计算提供真实的解释，并形成可检验的神经科学假设。

ABSTRACT

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 computational mechanisms 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.

研究动机与目标

• 在神经建模中动机说明不仅仅是输入-输出的准确性，需要对机制进行解释。
• 开发一种从在视网膜数据上训练的深度CNN中提取简化、可解释的子网络的方法。
• 展示简化模型能够再现已知的视网膜现象并产生新的可检验假设。
• 证明深度网络不仅能提供预测性能，还能提供对中间视网膜计算的概念性洞察。

提出的方法

• 将视网膜响应表示为 r(t) = F[s(t)]，并通过沿着刺激路径的输入归因对 r(t) 进行分解以获得精确贡献 A_xyΔt（方程1）。
• 将归因扩展到第一层隐藏单元以获得 r(t) = Σ_cxy [G_cxy(s)] (W_cxy^{[1]} ∘ s) = Σ A_cxy (Equation 2).
• 利用刺激不变性显著降低维数（例如 OSR/潜伏期：10,368 → 8 通道；运动翻转/预测：10,368 → 288；方程3–4）。
• 仅使用由大归因识别出的重要子单元来构建一隐藏层的简化模型。
• 将该简化程序应用于每个人工刺激类别，以推导与先前视网膜理论一致（并扩展）的机制性解释。

实验结果

研究问题

• RQ1 在对人工刺激进行测试时，训练于自然视网膜刺激的深度CNN是否能揭示与生物视网膜相同的计算机制？
• RQ2 如何通过模型简化和归因揭示能够解释复杂视网膜响应的可解释、最小化的电路？
• RQ3 提取的 OSR、潜伏期编码、运动翻转和运动预测的机制是否与先前的实验发现一致，并提供新的可检验假设？
• RQ4 在单一简化模型中，统一的三通道框架（ON/OFF、快/慢）是否能够解释多样的视网膜计算？

主要发现

• 一个三通道的简化模型（1个OFF，2个ON）捕捉了 Omitted Stimulus Response，其峰值时序随闪烁频率变化而移动。
• 潜伏期编码可由双ON/OFF通道及延迟抑制塑造的响应峰来解释。
• 运动翻转由跨空间的两个子单元通过非线性下游权重产生突发，从而产生固定的潜伏期来解释。
• 运动预测由兴奋性输入加上对运动方向敏感的抑制共同使峰值沿运动方向提前而产生。
• 在所有情况中，简化模型给出了与既有工作一致的机制性解释并提供可实验检验的假设，验证深度CNN作为神经科学科学假设生成工具的可用性。