Abstract
Understanding how the brain learns may be informed by studying biologically plausible learning rules. These rules, often approximating gradient descent learning to respect biological constraints such as locality, must meet two critical criteria to be considered an appropriate brain model: (1) good neuroscience task performance and (2) alignment with neural recordings. While extensive research has assessed the first criterion, the second remains underexamined. Employing methods such as Procrustes analysis on well-known neuroscience datasets, this study demonstrates the existence of a biologically plausible learning rule -- namely e-prop, which is based on gradient truncation and has demonstrated versatility across a wide range of tasks -- that can achieve neural data similarity comparable to Backpropagation Through Time (BPTT) when matched for task accuracy. Our findings also reveal that model architecture and initial conditions can play a more significant role in determining neural similarity than the specific learning rule. Furthermore, we observe that BPTT-trained models and their biologically plausible counterparts exhibit similar dynamical properties at comparable accuracies. These results underscore the substantial progress made in developing biologically plausible learning rules, highlighting their potential to achieve both competitive task performance and neural data similarity.
Abstract (translated)
理解大脑如何学习可能需要研究生物上合理的学习规则。这些规则通常会模仿梯度下降学习，以遵守诸如局部性等生物学约束条件。为了被认为是一个合适的脑模型，这类规则必须满足两个关键标准：（1）良好的神经科学任务表现；以及（2）与神经记录数据的契合度。尽管许多研究已经评估了第一个标准，但第二个标准则相对较少被探讨。 通过在知名神经科学研究数据集中应用诸如普罗克鲁斯特斯分析等方法，本研究证明了一个生物上合理的学习规则——即基于梯度截断的e-prop（Efficient Propagation），它能够跨广泛任务展示出灵活性。当准确率相匹配时，该学习规则可以达到与通过时间反向传播算法（Backpropagation Through Time, BPTT）相似的神经数据一致性。 此外，我们的研究还揭示了模型架构和初始条件对于确定神经相似度的影响可能比具体的学习规则更为重要。我们进一步观察到，在准确率相同的情况下，使用BPTT训练得到的模型及其生物合理学习规则对应的模型表现出类似的动态特性。 这些结果突显了在开发生物学上合理的学习规则方面所取得的重大进展，并强调其不仅能够实现竞争性的任务表现，还能达到与神经记录数据相似性。
URL
https://arxiv.org/abs/2506.06904
