Advances in experimental neuroscience have transformed our ability to explore the structure and function of neural circuits. At the same time, advances in machine learning have unleashed the remarkable computational power of artificial neural networks (ANNs). While these two fields have different tools and applications, they present a similar challenge: namely, understanding how information is embedded and processed through high-dimensional representations to solve complex tasks. One approach to addressing this challenge is to utilize mathematical and computational tools to analyze the geometry of these high-dimensional representations, i.e., neural population geometry. We review examples of geometrical approaches providing insight into the function of biological and artificial neural networks: representation untangling in perception, a geometric theory of classification capacity, disentanglement and abstraction in cognitive systems, topological representations underlying cognitive maps, dynamic untangling in motor systems, and a dynamical approach to cognition. Together, these findings illustrate an exciting trend at the intersection of machine learning, neuroscience, and geometry, in which neural population geometry provides a useful population-level mechanistic descriptor underlying task implementation. Importantly, geometric descriptions are applicable across sensory modalities, brain regions, network architectures and timescales. Thus, neural population geometry has the potential to unify our understanding of structure and function in biological and artificial neural networks, bridging the gap between single neurons, populations and behavior.
Bio-inspired AI: Integrating Biological Complexity into Artificial Intelligence
McGovern Institute for Brain Research, MIT（麻省理工学院麦戈文脑科学研究所）；Allen Discovery Center at Tufts University（塔夫茨大学艾伦发现中心）；Center for Brains, Minds, and Machines, MIT（麻省理工学院脑、心智与机器中心）；Wyss Institute for Biologically Inspired Engineering, Harvard University（哈佛大学威斯生物启发工程研究所）
Replay in Deep Learning: Current Approaches and Missing Biological Elements
Rochester Institute of Technology（罗切斯特理工学院）；University of California at San Diego（加州大学圣地亚哥分校）；Salk Institute for Biological Studies（索尔克生物研究所）；Paige；Cornell Tech（康奈尔理工学院）
Adversarially trained neural representations may already be as robust as corresponding biological neural representations
McGovern Institute for Brain Research, MIT（麻省理工学院麦戈文脑研究所）；MIT（麻省理工学院）；Department of Brain and Cognitive Sciences, MIT（麻省理工学院脑与认知科学系）；Center for Brains, Minds and Machines, MIT（麻省理工学院脑、心智与机器中心）；Computer Science and Artificial Intelligence Laboratory, MIT（麻省理工学院计算机科学与人工智能实验室）；School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）；Harvard University（哈佛大学）；Purdue University（普渡大学）；Department of Electrical Engineering and Computer Science, MIT（麻省理工学院电气工程与计算机科学系）
Digital twin brain: a bridge between biological intelligence and artificial intelligence
Brainnetome Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所脑网络组研究中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Research Center for Augmented Intelligence, Zhejiang Lab（之江实验室增强智能研究中心）
Same Compression Principle, Different Geometry: Rate-Distortion Signatures Dissociate Biological and Artificial Visual Systems
Windreich Department of AI；Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA；Department of Computing, Imperial College London, London, UK；Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, NY, USA；Department of Neuroscience, Icahn School of Medicine at Mount Sinai, New York, NY, USA；Berkman Klein Center for Internet \& Society, Harvard University, Cambridge, MA, USA
Brain-inspired learning in artificial neural networks: a review
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Cambridge（剑桥大学）；Intel Labs（英特尔实验室）；ML Collective（机器学习联盟）；The Swiss AI Lab IDSIA（瑞士人工智能实验室IDSIA）；University of Maryland, College Park（马里兰大学帕克分校）；University of California, Santa Cruz（加州大学圣克鲁兹分校）
Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience
University of Cambridge（剑桥大学）；University of Oxford（牛津大学）；Imperial College London（帝国理工学院）；Massachusetts Institute of Technology（麻省理工学院）；Georgia Institute of Technology（佐治亚理工学院）；New York University（纽约大学）；Princeton University（普林斯顿大学）
