Masked Autoencoders Learn Perception-Relevant Representations from Resting State Neural Data

• URL: http://arxiv.org/abs/2607.22615v1
• Date: Mon, 15 Jun 2026 13:43:04 GMT
• Title: Masked Autoencoders Learn Perception-Relevant Representations from Resting State Neural Data
• Abstract summary: We pretrained a masked autoencoder on 14.6 hours of spontaneous multiunit activity from an intracortical array in a blind participant's V1.<n> Perception decoding accuracy reached 84.1% on a general psychometric task.<n>This work shows that spontaneous cortical activity is not noise; it contains rich, task-relevant structure.
• Score: 29.99775209501762
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Clinical neuroprosthetics face a data bottleneck: labeled perception trials are scarce while hours of spontaneous neural activity are largely underutilized. Here, we test whether self-supervised learning can use these unlabeled datasets to improve perception decoding. We pretrained a masked autoencoder on 14.6 hours of spontaneous multiunit activity from an intracortical array in a blind participant's V1. The model captured interpretable brain structure without supervision: V1's spatial organization and perceptual state separation both emerged purely from its latent representations. To test these features, we used linear probing (logistic regression on the frozen latents) to measure performance on the data with stimulation. Perception decoding accuracy reached 84.1% on a general psychometric task. On the more difficult threshold-level task, accuracy reached 64.0%. This work shows that spontaneous cortical activity is not noise; it contains rich, task-relevant structure. Unsupervised pretraining on this data is a promising strategy to improve neural decoding.

Related papers

• Automatic Neuronal Activity Segmentation in Fast Four Dimensional Spatio-Temporal Fluorescence Imaging using Bayesian Approach [5.344174933185375]
  We present a Deep Learning Framework to detect neuronal activities in 4Diz-temporal data obtained by light sheet microscopy.<n>Our approach accounts for the use of temporal information by calculating pixel wise correlation maps and combines it with spatial information given by mean summary image.
  arXiv  Detail & Related papers  (2025-12-22T05:08:52Z)
• Deep Learning for real-time neural decoding of grasp [0.0]
  We present a Deep Learning-based approach to the decoding of neural signals for grasp type classification. The main goal of the presented approach is to improve over state-of-the-art decoding accuracy without relying on any prior neuroscience knowledge.
  arXiv  Detail & Related papers  (2023-11-02T08:26:29Z)
• Learnable latent embeddings for joint behavioral and neural analysis [3.6062449190184136]
  We show that CEBRA can be used for the mapping of space, uncovering complex kinematic features, and rapid, high-accuracy decoding of natural movies from visual cortex. We validate its accuracy and demonstrate its utility for both calcium and electrophysiology datasets, across sensory and motor tasks, and in simple or complex behaviors across species.
  arXiv  Detail & Related papers  (2022-04-01T19:19:33Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Robust alignment of cross-session recordings of neural population activity by behaviour via unsupervised domain adaptation [1.2617078020344619]
  We introduce a model capable of inferring behaviourally relevant latent dynamics from previously unseen data recorded from the same animal. We show that unsupervised domain adaptation combined with a sequential variational autoencoder, trained on several sessions, can achieve good generalisation to unseen data.
  arXiv  Detail & Related papers  (2022-02-12T22:17:30Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Learning Personal Representations from fMRIby Predicting Neurofeedback Performance [52.77024349608834]
  We present a deep neural network method for learning a personal representation for individuals performing a self neuromodulation task, guided by functional MRI (fMRI) The representation is learned by a self-supervised recurrent neural network, that predicts the Amygdala activity in the next fMRI frame given recent fMRI frames and is conditioned on the learned individual representation.
  arXiv  Detail & Related papers  (2021-12-06T10:16:54Z)
• SOUL: An Energy-Efficient Unsupervised Online Learning Seizure Detection Classifier [68.8204255655161]
  Implantable devices that record neural activity and detect seizures have been adopted to issue warnings or trigger neurostimulation to suppress seizures. For an implantable seizure detection system, a low power, at-the-edge, online learning algorithm can be employed to dynamically adapt to neural signal drifts. SOUL was fabricated in TSMC's 28 nm process occupying 0.1 mm2 and achieves 1.5 nJ/classification energy efficiency, which is at least 24x more efficient than state-of-the-art.
  arXiv  Detail & Related papers  (2021-10-01T23:01:20Z)
• And/or trade-off in artificial neurons: impact on adversarial robustness [91.3755431537592]
  Presence of sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks. We define AND-like neurons and propose measures to increase their proportion in the network. Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.
  arXiv  Detail & Related papers  (2021-02-15T08:19:05Z)
• Using Convolutional Variational Autoencoders to Predict Post-Trauma Health Outcomes from Actigraphy Data [4.668948267866486]
  Depression and post-traumatic stress disorder (PTSD) are psychiatric conditions commonly associated with a traumatic event. In this work, we used locomotor activity captured from 1113 individuals who wore a research grade smartwatch post-trauma. A convolutional variational autoencoder (VAE) architecture was used for unsupervised feature extraction from actigraphy data.
  arXiv  Detail & Related papers  (2020-11-14T22:48:12Z)
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
  Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
  arXiv  Detail & Related papers  (2020-06-22T15:07:06Z)

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.