The spectacular results achieved in machine learning, including the recent advances in generative AI, rely on large data collections. On the opposite, intelligent processes in nature arises without the need for such collections, but simply by online processing of the environmental information. In particular, natural learning processes rely on mechanisms where data representation and learning are intertwined in such a way to respect spatiotemporal locality. This paper shows that such a feature arises from a pre-algorithmic view of learning that is inspired by related studies in Theoretical Physics. We show that the algorithmic interpretation of the derived "laws of learning", which takes the structure of Hamiltonian equations, reduces to Backpropagation when the speed of propagation goes to infinity. This opens the doors to machine learning studies based on full on-line information processing that are based the replacement of Backpropagation with the proposed spatiotemporal local algorithm.

利用大数据集合取得的机器学习的显著成果，尤其是生成式人工智能的最新进展，与自然界中的智能过程相对立，后者并不需要这样的数据集合，仅通过环境信息的在线处理即可，本文表明这种特征源于借鉴理论物理学的相关研究，展示了当传播速度趋于无穷大时，所推导的“学习规律”的算法解释退化为反向传播，这为基于完全在线信息处理的机器学习研究开辟了门路，其中使用了新提出的时空局部算法代替反向传播。

自然灵感的局部传播