用能量模型模拟大脑预测机制，实现生物合理且泛化性强的预测能力。
Predictive Learning in Energy-based Models with Attractor Structures
- 构建分层能量模型结合连续吸引子网络，模拟神经系统的预测与记忆过程。
- 在眼动、环境运动等多场景下准确预测已知与未知环境，性能媲美主流机器学习方法。
- 为理解大脑如何实现预测提供了可解释的生物合理性模型，适合神经科学与类脑智能研究者。
预测模型在理解大脑功能机制方面已取得显著进展。机器学习的最新发展进一步证明了预测在最优表征学习中的强大作用。然而，仍缺乏能够解释神经系统如何实现预测的生物合理模型。本文提出一种基于能量模型（EBM）的框架，用于捕捉神经系统在动作后对观测结果进行预测的复杂过程，涵盖预测、学习与推断。模型采用分层结构，并整合连续吸引子神经网络以实现记忆功能，构建出具有生物合理性的预测模型。实验评估表明，该模型在多种场景下表现优异：涵盖眼动、环境运动、头部转动及静态观察时环境变化等动作类型。模型不仅在训练过的环境中做出准确预测，还能对未见过的环境提供合理预测，其性能在多个任务中达到与主流机器学习方法相当的水平。本研究旨在深化对神经系统预测机制的理解。
原文摘要 · Abstract (English)
Predictive models are highly advanced in understanding the mechanisms of brain function. Recent advances in machine learning further underscore the power of prediction for optimal representation in learning. However, there remains a gap in creating a biologically plausible model that explains how the neural system achieves prediction. In this paper, we introduce a framework that employs an energy-based model (EBM) to capture the nuanced processes of predicting observation after action within the neural system, encompassing prediction, learning, and inference. We implement the EBM with a hierarchical structure and integrate a continuous attractor neural network for memory, constructing a biologically plausible model. In experimental evaluations, our model demonstrates efficacy across diverse scenarios. The range of actions includes eye movement, motion in environments, head turning, and static observation while the environment changes. Our model not only makes accurate predictions for environments it was trained on, but also provides reasonable predictions for unseen environments, matching the performances of machine learning methods in multiple tasks. We hope that this study contributes to a deep understanding of how the neural system performs prediction.
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。