Searcharxiv⌕ Search

arXiv subjects

Michael F. Bonner

Publications and source records attributed to Michael F. Bonner.

7 recordsLinked to original sources

Interpretable weight-space programming builds transparent transformers and brain encoding models

Neural networks are powerful predictors, yet their opacity limits their usefulness in science, where the goal is explanation rather than mere prediction. In neuroscience, for example, deep encoding models accurately predict brain activity in response to natural stimuli, but struggle to reveal which stimulus features drive those predictions. Here we introduce interpretable weight-space programming (iWSP), a method in which an LLM agent iteratively builds interpretable models by explicitly programming their weights and features in code, without gradient-based training (backpropagation). Without backpropagation to tune parameters, the agent must draw on its prior knowledge and reason over previous trials to hypothesize, hand-craft, and refine human-interpretable computations mirroring the workflow of a human scientist. LLM audits confirm the interpretability of the hand-crafted models. We first validate iWSP by tasking it with constructing transformers for canonical benchmarks such as arithmetic and sentiment classification, finding that LLM agents can successfully craft compact, accurate networks directly. Next, we apply iWSP to build neural encoding models across vision, language, and audition. In the visual cortex, iWSP outpredicts existing interpretable baselines, uncovers distinct computations across early/higher visual areas, and generalizes to unseen data. In language fMRI, iWSP surfaces a confound in the data and in auditory ECoG, it systematically discovers interpretable acoustic features that predict neural activity. Together, these results establish iWSP as a general paradigm for aligning high predictive performance with human-interpretable scientific discovery.

cs.CE↗

Characterizing universal object representations across vision models

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.

cs.CV↗

Extremely coarse learning objectives induce human-aligned representations in AI vision models

Artificial neural networks trained on visual tasks develop internal representations resembling those of the primate visual system, a discovery that has guided a decade of computational neuroscience. Research on building brain-aligned models has progressively embraced finer-grained learning ob- jectives, from object classification to contrastive self-supervised objectives that maximize distinc- tions among individual images. Yet the effect of learning-signal granularity on brain alignment remains largely unexamined. Here we systematically investigate how the granularity of a learning signal shapes representational alignment with human vision. We parametrically vary the number of training classes using a data-driven approach that partitions a set of training images into differ- ent numbers of categories via PCA-based splits of pretrained embeddings. We train hundreds of neural networks across convolutional and transformer architectures on these coarse classification tasks and compare their representations with human fMRI responses, macaque electrophysiology recordings, and human behavior. We find that networks trained to distinguish as few as eight broad categories learn representations that match or exceed the neural alignment of models distinguishing 1,000 classes. Even more strikingly, these coarsely trained networks align more closely with hu- man perceptual similarity judgments than all other models evaluated, including networks trained with fine-grained supervision or self-supervision as well as leading large-scale vision models. These results demonstrate that human-like visual representations can emerge from surprisingly simple learning objectives, reframing what learning signals vision may require and opening a path toward building AI systems that are more aligned with human perception.

cs.CV↗

Efficient coding along the visual hierarchy

Biological visual systems learn from limited experience, unlike deep learning models that rely on millions of training images. What learning principles make this possible? We tested whether efficient coding, the idea that neural representations capture the statistical structure of natural inputs, can build a hierarchy of human-aligned visual features from limited data. We developed an unsupervised learning procedure in which each layer of a deep network compresses its inputs onto the dominant modes of variation in natural images, using only local statistics and no labels, tasks, or backpropagation. This unsupervised procedure yields features that progress from edges and colors to textures and shapes. The features of this deep efficient coding model are readily recognized by human observers and are predictive of image-evoked fMRI responses in human visual cortex. Furthermore, a hybrid learning procedure that combines efficient coding with supervised fine-tuning yields better brain alignment in low-data settings and more rapid category learning. These findings suggest that efficient coding may shape representations across the entire visual hierarchy and help explain the data efficiency of biological vision.

cs.CV↗

High-dimensional structure underlying individual differences in naturalistic visual experience

How do different brains create unique visual experiences from identical sensory input? While neural representations vary across individuals, the fundamental architecture underlying these differences remains poorly understood. Here, we reveal that individual visual experience emerges from a high-dimensional neural geometry across the visual cortical hierarchy. Using spectral decomposition of fMRI responses during naturalistic movie viewing, we find that idiosyncratic neural patterns persist across multiple orders of magnitude of latent dimensions. Remarkably, each dimensional range encodes qualitatively distinct aspects of individual processing, and this multidimensional neural geometry predicts subsequent behavioral differences in memory recall. These fine-grained patterns of inter-individual variability cannot be reduced to those detected by conventional intersubject correlation measures. Our findings demonstrate that subjective visual experience arises from information integrated across an expansive multidimensional manifold. This geometric framework offers a powerful new lens for understanding how diverse brains construct unique perceptual worlds from shared experiences.

q-bio.NC↗

Universal scale-free representations in human visual cortex

How does the human brain encode complex visual information? While previous research has characterized individual dimensions of visual representation in cortex, we still lack a comprehensive understanding of how visual information is organized across the full range of neural population activity. Here, analyzing fMRI responses to natural scenes across multiple individuals, we discover that neural representations in human visual cortex follow a remarkably consistent scale-free organization -- their variance systematically decays as a power law, detected across four orders of magnitude of latent dimensions. This scale-free structure appears consistently across multiple visual regions and across individuals, suggesting it reflects a fundamental organizing principle of visual processing. Critically, when we align neural responses across individuals using hyperalignment, we find that these representational dimensions are largely shared between people, revealing a universal high-dimensional spectrum of visual information that emerges despite individual differences in brain anatomy and visual experience. Traditional analysis approaches in cognitive neuroscience have focused primarily on a small number of high-variance dimensions, potentially missing crucial aspects of visual representation. Our results demonstrate that visual information is distributed across the full dimensionality of cortical activity in a systematic way, suggesting we need to move beyond low-dimensional characterizations to fully understand how the brain represents the visual world. This work reveals a new fundamental principle of neural coding in human visual cortex and highlights the importance of examining neural representations across their full dimensionality.

q-bio.NC↗

Universal dimensions of visual representation

Do neural network models of vision learn brain-aligned representations because they share architectural constraints and task objectives with biological vision or because they learn universal features of natural image processing? We characterized the universality of hundreds of thousands of representational dimensions from visual neural networks with varied construction. We found that networks with varied architectures and task objectives learn to represent natural images using a shared set of latent dimensions, despite appearing highly distinct at a surface level. Next, by comparing these networks with human brain representations measured with fMRI, we found that the most brain-aligned representations in neural networks are those that are universal and independent of a network's specific characteristics. Remarkably, each network can be reduced to fewer than ten of its most universal dimensions with little impact on its representational similarity to the human brain. These results suggest that the underlying similarities between artificial and biological vision are primarily governed by a core set of universal image representations that are convergently learned by diverse systems.

q-bio.NC↗