Sparse Autoencoders Bridge The Deep Learning Model and The Brain

• URL: http://arxiv.org/abs/2506.11123v1
• Date: Tue, 10 Jun 2025 06:35:14 GMT
• Title: Sparse Autoencoders Bridge The Deep Learning Model and The Brain
• Authors: Ziming Mao, Jia Xu, Zeqi Zheng, Haofang Zheng, Dabing Sheng, Yaochu Jin, Guoyuan Yang,
• Abstract summary: We present SAE-BrainMap, a novel framework that aligns deep learning visual model representations with voxel-level fMRI responses.<n>It is found that ViT-B/16$_CLIP$ tends to utilize low-level information to generate high-level semantic information in the early layers.<n>Our results establish a direct, downstream-task-free bridge between deep neural networks and human visual cortex, offering new insights into model interpretability.
• Score: 18.058358411706052
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present SAE-BrainMap, a novel framework that directly aligns deep learning visual model representations with voxel-level fMRI responses using sparse autoencoders (SAEs). First, we train layer-wise SAEs on model activations and compute the correlations between SAE unit activations and cortical fMRI signals elicited by the same natural image stimuli with cosine similarity, revealing strong activation correspondence (maximum similarity up to 0.76). Depending on this alignment, we construct a voxel dictionary by optimally assigning the most similar SAE feature to each voxel, demonstrating that SAE units preserve the functional structure of predefined regions of interest (ROIs) and exhibit ROI-consistent selectivity. Finally, we establish fine-grained hierarchical mapping between model layers and the human ventral visual pathway, also by projecting voxel dictionary activations onto individual cortical surfaces, we visualize the dynamic transformation of the visual information in deep learning models. It is found that ViT-B/16$_{CLIP}$ tends to utilize low-level information to generate high-level semantic information in the early layers and reconstructs the low-dimension information later. Our results establish a direct, downstream-task-free bridge between deep neural networks and human visual cortex, offering new insights into model interpretability.

Related papers

• Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex [5.283925904540581]
  BraInCoRL uses in-context learning to predict voxelwise neural responses from few-shot examples.<n>We show that BraInCoRL consistently outperforms existing voxelwise encoder designs in a low-data regime.<n>BraInCoRL facilitates better interpretability of neural signals in higher visual cortex by attending to semantically relevant stimuli.
  arXiv  Detail & Related papers  (2025-05-21T17:59:41Z)
• Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation [56.34634121544929]
  In this study, we first construct the brain-effective network via the dynamic causal model. We then introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE) This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks.
  arXiv  Detail & Related papers  (2024-05-21T20:37:07Z)
• Joint-Embedding Masked Autoencoder for Self-supervised Learning of Dynamic Functional Connectivity from the Human Brain [16.62883475350025]
  Graph Neural Networks (GNNs) have shown promise in learning dynamic functional connectivity for distinguishing phenotypes from human brain networks.<n>We introduce the Spatio-Temporal Joint Embedding Masked Autoencoder (ST-JEMA), drawing inspiration from the Joint Embedding Predictive Architecture (JEPA) in computer vision.
  arXiv  Detail & Related papers  (2024-03-11T04:49:41Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• Controllable Mind Visual Diffusion Model [58.83896307930354]
  Brain signal visualization has emerged as an active research area, serving as a critical interface between the human visual system and computer vision models. We propose a novel approach, referred to as Controllable Mind Visual Model Diffusion (CMVDM) CMVDM extracts semantic and silhouette information from fMRI data using attribute alignment and assistant networks. We then leverage a control model to fully exploit the extracted information for image synthesis, resulting in generated images that closely resemble the visual stimuli in terms of semantics and silhouette.
  arXiv  Detail & Related papers  (2023-05-17T11:36:40Z)
• A Generic Shared Attention Mechanism for Various Backbone Neural Networks [53.36677373145012]
  Self-attention modules (SAMs) produce strongly correlated attention maps across different layers. Dense-and-Implicit Attention (DIA) shares SAMs across layers and employs a long short-term memory module. Our simple yet effective DIA can consistently enhance various network backbones.
  arXiv  Detail & Related papers  (2022-10-27T13:24:08Z)
• Top-down inference in an early visual cortex inspired hierarchical Variational Autoencoder [0.0]
  We exploit advances in Variational Autoencoders to investigate the early visual cortex with sparse coding hierarchical VAEs trained on natural images. We show that representations similar to the one found in the primary and secondary visual cortices naturally emerge under mild inductive biases. We show that a neuroscience-inspired choice of the recognition model is critical for two signatures of computations with generative models.
  arXiv  Detail & Related papers  (2022-06-01T12:21:58Z)
• Self-supervised models of audio effectively explain human cortical responses to speech [71.57870452667369]
  We capitalize on the progress of self-supervised speech representation learning to create new state-of-the-art models of the human auditory system. We show that these results show that self-supervised models effectively capture the hierarchy of information relevant to different stages of speech processing in human cortex.
  arXiv  Detail & Related papers  (2022-05-27T22:04:02Z)
• Insights on Neural Representations for End-to-End Speech Recognition [28.833851817220616]
  End-to-end automatic speech recognition (ASR) models aim to learn a generalised speech representation. Previous investigations of network similarities using correlation analysis techniques have not been explored for End-to-End ASR models. This paper analyses and explores the internal dynamics between layers during training with CNN, LSTM and Transformer based approaches.
  arXiv  Detail & Related papers  (2022-05-19T10:19:32Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.