Dimensions underlying the representational alignment of deep neural networks with humans
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）；Donders Institute for Brain, Cognition and Behaviour（唐德斯脑、认知与行为研究所）；Technische Universität Berlin（柏林工业大学）；Berlin Institute for the Foundations of Learning and Data (BIFOLD)（柏林学习与数据基础研究所）；Justus Liebig University（尤斯图斯·李比希大学）；Center for Mind, Brain and Behavior, Universities of Marburg, Giessen, and Darmstadt（马尔堡、吉森和达姆施塔特大学心智、大脑与行为中心）；Google DeepMind（谷歌DeepMind）
Florian P. Mahner, Lukas Muttenthaler, Umut Güçlü, Martin N. Hebart
Determining the similarities and differences between humans and artificial intelligence (AI) is an important goal both in computational cognitive neuroscience and machine learning, promising a deeper understanding of human cognition and safer, more reliable AI systems. Much previous work comparing representations in humans and AI has relied on global, scalar measures to quantify their alignment. However, without explicit hypotheses, these measures only inform us about the degree of alignment, not the factors that determine it. To address this challenge, we propose a generic framework to compare human and AI representations, based on identifying latent representational dimensions underlying the same behavior in both domains. Applying this framework to humans and a deep neural network (DNN) model of natural images revealed a low-dimensional DNN embedding of both visual and semantic dimensions. In contrast to humans, DNNs exhibited a clear dominance of visual over semantic properties, indicating divergent strategies for representing images. While in-silico experiments showed seemingly consistent interpretability of DNN dimensions, a direct comparison between human and DNN representations revealed substantial differences in how they process images. By making representations directly comparable, our results reveal important challenges for representational alignment and offer a means for improving their comparability.
Neural networks trained on standard image classification data sets are shown to be less resistant to data set bias. It is necessary to comprehend the behavior objective function that might correspond to superior performance for data with biases. However, there is little research on the selection of the objective function and its representational structure when trained on data set with biases. In this paper, we investigate the performance and internal representational structure of convolution-based neural networks (e.g., ResNets) trained on biased data using various objective functions. We spec…
Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
UC Berkeley（伯克利大学）；Technical University Munich, MCML（慕尼黑技术大学）；University of Tübingen, Tübingen AI Center（图宾根大学）；Toyota Technical Institute at Chicago（芝加哥丰田技术研究所）
Achieving More Human Brain-Like Vision via Human EEG Representational Alignment
Department of Psychology, The Ohio State University（心理学系，俄亥俄州立大学）；McGovern Institute for Brain Research, Massachusetts Institute of Technology（脑科学研究所，麻省理工学院）；Department of Neuroscience, The University of Texas at Dallas（神经科学系，德克萨斯大学达拉斯分校）
Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models
The School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China（人工智能与自动化学院，华中科技大学，武汉430074，中国）；Department of Computer Science and Engineering, University of Nevada, Reno, NV, USA（计算机科学与工程系，内华达大学里诺分校，内华达州，美国）
On the dynamic evolution of CLIP texture-shape bias and its relationship to human alignment and model robustness
Image Processing Lab, Universitat de Valencia, Spain（瓦伦西亚大学图像处理实验室）；Centro de Biomateriales e Ingenieria Tisular, Universitat Politecnica de Valencia, Spain（瓦伦西亚理工大学生物材料与组织工程中心）；Computer Vision Center, Spain（西班牙计算机视觉中心）；Universitat Autònoma de Barcelona, Spain（巴塞罗那自治大学）
Previous work has largely considered the fairness of image captioning systems through the underspecified lens of "bias." In contrast, we present a set of techniques for measuring five types of representational harms, as well as the resulting measurements obtained for two of the most popular image captioning datasets using a state-of-the-art image captioning system. Our goal was not to audit this image captioning system, but rather to develop normatively grounded measurement techniques, in turn providing an opportunity to reflect on the many challenges involved. We propose multiple measurement …
Similarity-based representation factorization for revealing interpretable dimensions in representational data
Max Planck Institute for Human Cognitive and Brain Sciences（人类认知与脑科学最大平面研究所）；National Institute of Mental Health（心理健康国家研究所）；Justus Liebig University Giessen（吉森约斯特-利普大学）；Center for Mind, Brain and Behavior（心智、脑与行为中心）
Escaping Plato's Cave: JAM for Aligning Independently Trained Vision and Language Models
Computation and Neural Systems（计算与神经系统）；California Institute of Technology（加利福尼亚理工学院）；Computation and Mathematical Sciences（计算与数学科学）；Google DeepMind（谷歌DeepMind）
A central challenge in developing versatile machine learning systems is catastrophic forgetting: a model trained on tasks in sequence will suffer significant performance drops on earlier tasks. Despite the ubiquity of catastrophic forgetting, there is limited understanding of the underlying process and its causes. In this paper, we address this important knowledge gap, investigating how forgetting affects representations in neural network models. Through representational analysis techniques, we find that deeper layers are disproportionately the source of forgetting. Supporting this, a study of…
Deep Models, Shallow Alignment: Uncovering the Granularity Mismatch in Neural Decoding
Dept. of Electrical & Computer Engineering, University of Pittsburgh, USA（宾夕法尼亚大学电气与计算机工程系）；Dept. of Biomedical Engineering, Tsinghua University, China（清华大学生物医学工程系）；Dept. of Neurology, University of Southern California, USA（美国南加州大学神经病学系）；Dept. of Computer Science, University of Texas Rio Grande Valley, USA（德克萨斯理工大学里奥格兰德谷分校计算机科学系）
Neural Functional Alignment Space: Brain-Referenced Representation of Artificial Neural Networks
Tandon School of Engineering, New York University（纽约大学工程学院）；School of Computing, University of Georgia（佐治亚大学计算机学院）；Department of Biomedical Engineering, New Jersey Institute of Technology（新泽西理工学院生物医学工程系）；The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for NeuroInformation,School of Life Science and Technology, University of Electronic Science and Technology of China（成都脑科学研究所临床医院，国家神经信息重点实验室，电子科技大学生命科学与技术学院）
