Martin N. Hebart

Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller et al. · berkeley, cambridge

Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the similarity between the representations formed by these diverse systems? Do similarities in representations then translate into similar behavior? If so, then how can a system's representations be modified to better match those of another system? These questions pertaining to the study of representational alignment are at the heart of some of the most promising research areas in contemporary cognitive science, neuroscience, and machine learning. In this Perspective, we survey the exciting recent developments in representational alignment research in the fields of cognitive science, neuroscience, and machine learning. Despite their overlapping interests, there is limited knowledge transfer between these fields, so work in one field ends up duplicated in another, and useful innovations are not shared effectively. To improve communication, we propose a unifying framework that can serve as a common language for research on representational alignment, and map several streams of existing work across fields within our framework. We also lay out open problems in representational alignment where progress can benefit all three of these fields. We hope that this paper will catalyze cross-disciplinary collaboration and accelerate progress for all communities studying and developing information processing systems.

Lukas Muttenthaler, Charles Y. Zheng, Patrick McClure et al.

A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task. VICE uses variational inference to obtain sparse, non-negative representations of object concepts with uncertainty estimates for the embedding values. These estimates are used to automatically select the dimensions that best explain the data. We derive a PAC learning bound for VICE that can be used to estimate generalization performance or determine a sufficient sample size for experimental design. VICE rivals or outperforms its predecessor, SPoSE, at predicting human behavior in the triplet odd-one-out task. Furthermore, VICE's object representations are more reproducible and consistent across random initializations, highlighting the unique advantage of using VICE for deriving interpretable embeddings from human behavior.

Florian P. Mahner, Ka Chun Lam, Francisco Pereira et al.

The study of representations is widespread across fields, including neuroscience, psychology, and artificial intelligence. While representations are often studied and compared through similarities between stimuli, current methods provide only limited access to the dimensions that shape these representations and are often limited in interpretability. To overcome these challenges, here we introduce Similarity-Based Representation Factorization (SRF), a general computational method for recovering low-dimensional, non-negative, interpretable embeddings from similarity matrices derived from measured data. Across simulations and many neural, behavioral, and computational datasets, SRF recovers interpretable dimensions from diverse forms of representational data, even for very sparsely sampled, incomplete data. The dimensions derived from these datasets match those obtained by task-specific models, predict independent behavioral properties, improve exploratory analysis, and offer higher power for confirmatory hypothesis testing than comparing similarity matrices. Together, these results establish SRF as a general-purpose method with broad applications for uncovering, understanding, and leveraging the dimensions underlying representations.

Florian P. Mahner, Johannes Roth, Ka Chun Lam et al.

Deep neural networks trained with different architectures, objectives, and datasets have been reported to converge on similar visual representations. However, what remains unknown is which visual properties models actually converge on and which factors may underlie this convergence. To address this, we decompose the object similarity structure of 162 diverse vision models into a small set of non-negative dimensions. To determine universal versus model-specific dimensions, we then estimate how often each dimension reappears across models. In contrast to model-specific dimensions, universal dimensions are more interpretable and more strongly driven by conceptual image properties, indicating the relevance of interpretability and semantic content as implicit factors driving universality across models. Differences in architecture, objective function, training data, model size, and model performance do not explain the emergence of universal dimensions. However, models with more universal dimensions also better predict macaque IT activity and human similarity judgments, suggesting that universality reflects representations relevant to biological vision. These findings have important implications for understanding the emergent representations underlying deep neural network models and their alignment with biological vision.

Marie St-Laurent, Basile Pinsard, Oliver Contier et al.

Data-hungry neuro-AI modelling requires ever larger neuroimaging datasets. CNeuroMod-THINGS meets this need by capturing neural representations for a wide set of semantic concepts using well-characterized images in a new densely-sampled, large-scale fMRI dataset. Importantly, CNeuroMod-THINGS exploits synergies between two existing projects: the THINGS initiative (THINGS) and the Courtois Project on Neural Modelling (CNeuroMod). THINGS has developed a common set of thoroughly annotated images broadly sampling natural and man-made objects which is used to acquire a growing collection of large-scale multimodal neural responses. Meanwhile, CNeuroMod is acquiring hundreds of hours of fMRI data from a core set of participants during controlled and naturalistic tasks, including visual tasks like movie watching and videogame playing. For CNeuroMod-THINGS, four CNeuroMod participants each completed 33-36 sessions of a continuous recognition paradigm using approximately 4000 images from the THINGS stimulus set spanning 720 categories. We report behavioural and neuroimaging metrics that showcase the quality of the data. By bridging together large existing resources, CNeuroMod-THINGS expands our capacity to model broad slices of the human visual experience.

Florian P. Mahner, Lukas Muttenthaler, Umut Güçlü et al.

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.

Hannes Hansen, Martin N. Hebart

Semantic features have been playing a central role in investigating the nature of our conceptual representations. Yet the enormous time and effort required to empirically sample and norm features from human raters has restricted their use to a limited set of manually curated concepts. Given recent promising developments with transformer-based language models, here we asked whether it was possible to use such models to automatically generate meaningful lists of properties for arbitrary object concepts and whether these models would produce features similar to those found in humans. To this end, we probed a GPT-3 model to generate semantic features for 1,854 objects and compared automatically-generated features to existing human feature norms. GPT-3 generated many more features than humans, yet showed a similar distribution in the types of generated features. Generated feature norms rivaled human norms in predicting similarity, relatedness, and category membership, while variance partitioning demonstrated that these predictions were driven by similar variance in humans and GPT-3. Together, these results highlight the potential of large language models to capture important facets of human knowledge and yield a new approach for automatically generating interpretable feature sets, thus drastically expanding the potential use of semantic features in psychological and linguistic studies.

Charles Y. Zheng, Francisco Pereira, Chris I. Baker et al.

To study how mental object representations are related to behavior, we estimated sparse, non-negative representations of objects using human behavioral judgments on images representative of 1,854 object categories. These representations predicted a latent similarity structure between objects, which captured most of the explainable variance in human behavioral judgments. Individual dimensions in the low-dimensional embedding were found to be highly reproducible and interpretable as conveying degrees of taxonomic membership, functionality, and perceptual attributes. We further demonstrated the predictive power of the embeddings for explaining other forms of human behavior, including categorization, typicality judgments, and feature ratings, suggesting that the dimensions reflect human conceptual representations of objects beyond the specific task.