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.
How much neuroscience does a neuroscientist need to know?
Gatsby Computational Neuroscience Unit, University College London（伦敦大学学院高斯比计算神经科学单元）；Department of Experimental Psychology, University of Oxford（牛津大学实验心理学系）
Decoding Alignment without Encoding Alignment: A critique of similarity analysis in neuroscience
University of Tübingen（蒂宾根大学）；ELLIS Institute Tübingen（蒂宾根 ELLS 研究所）；Tübingen AI Center（蒂宾根人工智能中心）；School of Science & Technology, IE University（IE 大学科学与技术学院）；The Kempner Institute for Natural and Artificial Intelligence, Harvard University（哈佛大学肯普纳自然与人工智能研究所）；Yale（耶鲁大学）
Toward a mechanistic understanding of inference in visual cortex and diffusion models
Dept. of Electrical Engineering and Computer Science, UC Berkeley（加州大学伯克利分校电气工程与计算机科学系）；Helen Wills Neuroscience Institute, UC Berkeley（加州大学伯克利分校海伦·威尔斯神经科学研究所）；Herbert Wertheim School of Optometry and Vision Science, UC Berkeley（加州大学伯克利分校赫伯特·韦特海姆视觉科学学院）；Redwood Center for Theoretical Neuroscience, UC Berkeley（加州大学伯克利分校红木理论神经科学中心）；Flatiron Institute（Flatiron研究所）；Dept. of Electrical and Computer Engineering, UC Davis（加州大学戴维斯分校电气与计算机工程系）
Inferring Mechanisms from Bits: Promises and Pitfalls of Higher-Order Information in Cognitive Science
Brain and Cognition Center, University of Amsterdam（阿姆斯特丹大学脑与认知中心）；Department of Psychology, University of Cambridge（剑桥大学心理学系）；Department of Psychology, Queen Mary University of London（伦敦大学女王学院心理学系）；Department of Computing, Imperial College London（帝国理工学院计算系）；Vermont Complex Systems Institute, University of Vermont（佛蒙特大学佛蒙特复杂系统研究所）；Department of Psychological and Brain Sciences, Indiana University（印第安纳大学心理与脑科学系）；School of Psychology and Neuroscience, University of Glasgow（格拉斯哥大学心理与神经科学学院）；CINPSI Neurocog, Faculty of Health Sciences, Universidad Católica del Maule（马乌莱天主教大学健康科学学院CINPSI神经认知）；Neuroscience Center, Helsinki Institute of Life Science, University of Helsinki（赫尔辛基大学生命科学研究所神经科学中心）
Reconstruction of Natural Visual Scenes from Neural Spikes with Deep Neural Networks
National Engineering Laboratory for Video Technology, School of Electronics Engineering and Computer Science, Peking University（北京大学电子信息工程学院视频技术国家工程实验室）；Peng Cheng Laboratory（鹏城实验室）；Centre for Systems Neuroscience, Department of Neuroscience, Psychology and Behaviour, University of Leicester（莱斯特大学神经科学、心理学与行为学系系统神经科学中心）
