用大模型理解大脑，关键是从预测转向解释机制。
From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?
- 用海量数据预训练大模型，无需人工标注。
- 模型预测准确，但需揭示神经活动背后的计算原理。
- 适合脑科学与人工智能交叉研究者参考。
生成式预训练（即ChatGPT中的“GPT”）使语言模型能够从大量互联网文本中无监督学习，推动了人工智能的突破。这一方法让深度神经网络从大规模非结构化数据中学习。我们称这些可适应多种任务的大规模预训练系统为基础模型，它们正被越来越多地应用于脑科学领域。这些模型展现出强大的预测能力，激发了人们对揭示计算原理的期望。然而，仅靠预测成功并不能保证科学理解。本文概述了基础模型在脑科学中的有效整合路径，强调其潜力与局限性。核心挑战在于从预测迈向解释：将模型的计算过程与神经活动及认知机制相联系。
原文摘要 · Abstract (English)
Generative pretraining (the "GPT" in ChatGPT) enables language models to learn from vast amounts of internet text without human supervision. This approach has driven breakthroughs across AI by allowing deep neural networks to learn from massive, unstructured datasets. We use the term foundation models to refer to large pretrained systems that can be adapted to a wide range of tasks within and across domains, and these models are increasingly applied beyond language to the brain sciences. These models achieve strong predictive accuracy, raising hopes that they might illuminate computational principles. But predictive success alone does not guarantee scientific understanding. Here, we outline how foundation models can be productively integrated into the brain sciences, highlighting both their promise and their limitations. The central challenge is to move from prediction to explanation: linking model computations to mechanisms underlying neural activity and cognition.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。