AI 中文总结
该研究提出前向-前向算法的循环变体，从局部学习规则产生预测编码关键原则，为神经科学与机器学习搭建新桥梁。
AI 中文摘要
分层预测编码提出了一种引人注目的大脑计算假说，认为大脑皮层构建分层预测以最小化惊喜，但多数模型依赖于错误编码神经元或生物合理性不明确的生成建模。本文研究了一种生物合理的框架，其中预测编码的功能目标源于局部对比学习和简单的活动抵消。基于近期机器学习进展，我们提出了前向-前向（FF）算法的循环变体，其目标函数倒置，可增加负数据的活动。该设置在各层产生预测表征，捕捉了大脑皮层计算的标志性特征，如自上而下调制和惊喜信号。我们的结果表明，预测编码的关键原则可从简单的局部学习规则中产生，为神经科学与机器学习提供了新的桥梁。
英文摘要
Hierarchical predictive coding proposes a compelling hypothesis of brain computation, suggesting that the cortex builds layered predictions to minimize surprise. Yet most models rely on error-coding neurons or generative modeling of unclear biological plausibility. Here, we examine a biologically plausible framework in which the functional goals of predictive coding emerge from local contrastive learning and simple activity cancellation. Building on recent machine learning advances, we present a recurrent variant of the Forward-Forward (FF) algorithm with an inverted objective that increases activity for negative data. This setup yields predictive representations across layers, capturing hallmark features of cortical computation such as top-down modulation and surprise signaling. Our results suggest that key principles of predictive coding can emerge from simple, local learning rules, offering a new bridge between neuroscience and machine learning.
