Scholarlink

<p>In human neuroscience, machine learning can help reveal lower-dimensional neural representations relevant to subjects’ behavior. However, state-of-the-art models typically require large datasets to train, and so are prone to overfitting on human neuroimaging data that often possess few samples but many input dimensions. Here, we capitalized on the fact that the features we seek in human neuroscience are precisely those relevant to subjects’ behavior rather than noise or other irrelevant factors. We thus developed a Task-Relevant Autoencoder via Classifier Enhancement (TRACE) designed to identify behaviorally-relevant target neural patterns. We benchmarked TRACE against a standard autoencoder and other models for two severely truncated machine learning datasets (to match the data typically available in functional magnetic resonance imaging [fMRI] data for an individual subject), then evaluated all models on fMRI data from 59 subjects who observed animals and objects. TRACE outperformed alternative models nearly unilaterally, showing up to 12% increased classification accuracy and up to 56% improvement in discovering “cleaner”, task-relevant representations. These results showcase TRACE’s potential for a wide variety of data related to human behavior.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Task relevant autoencoding enhances machine learning for human neuroscience

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年1月8日

查看全文
  • Seyedmehdi Orouji,
  • Vincent Taschereau-Dumouchel,
  • Aurelio Cortese,
  • Brian Odegaard,
  • Cody Cushing,
  • Mouslim Cherkaoui,
  • Mitsuo Kawato,
  • Hakwan Lau,
  • Megan A. K. Peters

摘要

In human neuroscience, machine learning can help reveal lower-dimensional neural representations relevant to subjects’ behavior. However, state-of-the-art models typically require large datasets to train, and so are prone to overfitting on human neuroimaging data that often possess few samples but many input dimensions. Here, we capitalized on the fact that the features we seek in human neuroscience are precisely those relevant to subjects’ behavior rather than noise or other irrelevant factors. We thus developed a Task-Relevant Autoencoder via Classifier Enhancement (TRACE) designed to identify behaviorally-relevant target neural patterns. We benchmarked TRACE against a standard autoencoder and other models for two severely truncated machine learning datasets (to match the data typically available in functional magnetic resonance imaging [fMRI] data for an individual subject), then evaluated all models on fMRI data from 59 subjects who observed animals and objects. TRACE outperformed alternative models nearly unilaterally, showing up to 12% increased classification accuracy and up to 56% improvement in discovering “cleaner”, task-relevant representations. These results showcase TRACE’s potential for a wide variety of data related to human behavior.