Different neural networks trained on the same dataset often learn similar input-output mappings with very different weights. Is there some correspondence between these neural network solutions? For linear networks, it has been shown that different instances of the same network architecture encode the same representational similarity matrix, and their neural activity patterns are connected by orthogonal transformations. However, it is unclear if this holds for non-linear networks. Using a shared response model, we show that different neural networks encode the same input examples as different orthogonal transformations of an underlying shared representation. We test this claim using both standard convolutional neural networks and residual networks on CIFAR10 and CIFAR100.
University of Maryland, College Park（马里兰大学帕克分校）；Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）；PUCRS（巴西圣保罗天主教大学）；The Alan Turing Institute（艾伦·图灵研究所）；University of Cambridge（剑桥大学）
A major challenge in studying robustness in deep learning is defining the set of ``meaningless'' perturbations to which a given Neural Network (NN) should be invariant. Most work on robustness implicitly uses a human as the reference model to define such perturbations. Our work offers a new view on robustness by using another reference NN to define the set of perturbations a given NN should be invariant to, thus generalizing the reliance on a reference ``human NN'' to any NN. This makes measuring robustness equivalent to measuring the extent to which two NNs share invariances, for which we pro…
Parameter symmetries determine representational geometry in overparameterized nonlinear networks
University of Tübingen（图宾根大学）；International Max Planck Research School for Intelligent Systems（国际马克斯·普朗克智能系统研究学院）；Allen Institute for Neural Dynamics（艾伦神经动力学研究所）；Gatsby Computational Neuroscience Unit, University College London（伦敦大学学院盖茨比计算神经科学中心）；Sainsbury Wellcome Centre, University College London（伦敦大学学院塞恩斯伯里惠康中心）；University of Alberta（阿尔伯塔大学）；Amii（艾伯塔机器智能研究所）
Geometry matters: insights from Ollivier Ricci Curvature and Ricci Flow into representational alignment through Ollivier-Ricci Curvature and Ricci Flow
Max Planck Institute for Human Cognitive and Brain Sciences（马克斯·普朗克人类认知与脑科学研究所）；Berlin School of Mind and Brain（柏林心智与脑学校）；Humboldt-Universität zu Berlin（洪堡大学）；Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI)（可扩展数据与人工智能中心（ScaDS.AI））
Zuckerman Mind Brain Behavior Institute, Columbia University, New York, NY, USA 10027（美国纽约州纽约市哥伦比亚大学祖克曼心智脑行为研究所）
Representational similarity analysis (RSA) has been shown to be an effective framework to characterize brain-activity profiles and deep neural network activations as representational geometry by computing the pairwise distances of the response patterns as a representational dissimilarity matrix (RDM). However, how to properly analyze and visualize the representational geometry as dynamics over the time course from stimulus onset to offset is not well understood. In this work, we formulated the pipeline to understand representational dynamics with RDM movies and Procrustes-aligned Multidimensio…
Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry
Center for Computational Neuroscience, Flatiron Institute（计算神经科学中心，扁铁研究所）；University of California, UCLA（加州大学，UCLA）；Center for Neural Science, New York University（神经科学中心，纽约大学）
Large language models reorganize representational geometry during in-context learning
School of Psychological and Brain Sciences, Georgia Tech（佐治亚理工学院心理与脑科学学院）；Department of Psychology, New York University（纽约大学心理学系）；Center of Excellence for Computational Cognition, Georgia Tech（佐治亚理工学院计算认知卓越中心）；Honda Research Institute（本田研究院）；Departments of Neuroscience and Psychology, The University of Texas at Austin（德克萨斯大学奥斯汀分校神经科学与心理学系）
We present an investigation into how representational losses can affect the drawings produced by artificial agents playing a communication game. Building upon recent advances, we show that a combination of powerful pretrained encoder networks, with appropriate inductive biases, can lead to agents that draw recognisable sketches, whilst still communicating well. Further, we start to develop an approach to help automatically analyse the semantic content being conveyed by a sketch and demonstrate that current approaches to inducing perceptual biases lead to a notion of objectness being a key feat…
Representational and Functional Robustness to Electrode Montages in EEG Foundation Models
Max Planck Institute for Human Cognitive and Brain Sciences（马克斯·普朗克人类认知与脑科学研究所）；ScaDS.AI Dresden/Leipzig（ScaDS.AI 德累斯顿/莱比锡）；BIFOLD–Berlin Institute for the Foundations of Learning and Data（BIFOLD–柏林学习与数据基础研究所）；Technische Universität Berlin（柏林工业大学）；Hector Fellow Academy（赫克托研究员学院）
Unsupervised discovery of the shared and private geometry in multi-view data
Department of Biomedical Engineering（生物医学工程系）；Johns Hopkins University（约翰霍普金斯大学）；Princeton Neuroscience Institute（普林斯顿神经科学研究所）；Princeton University（普林斯顿大学）；Department of Psychology and Brain Sciences（心理学与脑科学系）；University of Delaware（德雷塞尔大学）；Center for Imaging Science（成像科学中心）；Kavli Neurodiscovery Institute（Kavli神经发现研究所）
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
Shared Geometry Is Not Shared Physics: A Layerwise Test of the Platonic Representation Hypothesis in Astronomy
UniverseTBD；EleutherAI；INTI International College Penang（英迪国际学院槟城分院）；Center for Astrophysics, Harvard & Smithsonian（哈佛-史密森尼天体物理中心）；AstroAI；Space Telescope Science Institute（空间望远镜科学研究所）；Johns Hopkins University（约翰斯·霍普金斯大学）
Incheon National University（仁川大学）；Dain Technology, Inc.
Modern convolutional neural networks (CNNs) have massive identical convolution blocks, and, hence, recursive sharing of parameters across these blocks has been proposed to reduce the amount of parameters. However, naive sharing of parameters poses many challenges such as limited representational power and the vanishing/exploding gradients problem of recursively shared parameters. In this paper, we present a recursive convolution block design and training method, in which a recursively shareable part, or a filter basis, is separated and learned while effectively avoiding the vanishing/exploding…
Max Planck Institute for Mathematics in the Sciences（马克斯·普朗克数学科学研究所）；Leipzig University（莱比锡大学）；Santa Fe Institute（圣塔菲研究所）
Conditional restricted Boltzmann machines are undirected stochastic neural networks with a layer of input and output units connected bipartitely to a layer of hidden units. These networks define models of conditional probability distributions on the states of the output units given the states of the input units, parametrized by interaction weights and biases. We address the representational power of these models, proving results their ability to represent conditional Markov random fields and conditional distributions with restricted supports, the minimal size of universal approximators, the ma…
We present implicit displacement fields, a novel representation for detailed 3D geometry. Inspired by a classic surface deformation technique, displacement mapping, our method represents a complex surface as a smooth base surface plus a displacement along the base's normal directions, resulting in a frequency-based shape decomposition, where the high frequency signal is constrained geometrically by the low frequency signal. Importantly, this disentanglement is unsupervised thanks to a tailored architectural design that has an innate frequency hierarchy by construction. We explore implicit disp…
University of Pennsylvania（宾夕法尼亚大学）；Mila Québec AI Institute（米拉魁北克人工智能研究所）；McGill University（麦吉尔大学）
Deep neural networks implement a sequence of layer-by-layer operations that are each relatively easy to understand, but the resulting overall computation is generally difficult to understand. We consider a simple hypothesis for interpreting the layer-by-layer construction of useful representations: perhaps the role of each layer is to reformat information to reduce the "distance" to the desired outputs. With this framework, the layer-wise computation implemented by a deep neural network can be viewed as a path through a high-dimensional representation space. We formalize this intuitive idea of…
Barycentric alignment for instance-level comparison of neural representations
Department of XXX, University of YYY, Location, Country（YYY大学XXX系）；School of ZZZ, Institute of WWW, Location, Country（WWW研究所ZZZ学院）；Department of Electrical and Computer Engineering, UCSD（UCSD电子与计算机工程系）；Cognitive Science Department, UCSD（UCSD认知科学系）；Department of Computer Science（计算机科学系）
Relative Geometry of Neural Forecasters: Linking Accuracy and Alignment in Learned Latent Geometry
Max Planck Institute for Human Cognitive and Brain Sciences（马克斯·普朗克人类认知与脑科学研究所）；School of Embedded Composite Artificial Intelligence (SECAI)（嵌入式复合人工智能学院）；Leipzig University（莱比锡大学）；Max Planck Institute for Mathematics in the Sciences（马克斯·普朗克数学研究院）
Tracing the Representation Geometry of Language Models from Pretraining to Post-training
Computer Science, McGill University（麦吉尔大学计算机科学系）；Mila - Quebec AI Institute（魁北克人工智能研究所）；UC Berkeley（加州大学伯克利分校）；G o o g l e , Paradigms of Intelligence Team（谷歌，智能范式团队）；Mathematics and Statistics, Université de Montréal（蒙特利尔大学数学与统计学系）；Neurology & Neurosurgery and Montreal Neurological Institute, McGill University（神经病学与神经外科及蒙特利尔神经研究所，麦吉尔大学）；CIFAR Learning in Machines & Brains Program（CIFAR 机器与大脑学习计划）
