Despite the widespread adoption of Backpropagation algorithm-based Deep Neural Networks, the biological infeasibility of the BP algorithm could potentially limit the evolution of new DNN models. To find a biologically plausible algorithm to replace BP, we focus on the top-down mechanism inherent in the biological brain. Although top-down connections in the biological brain play crucial roles in high-level cognitive functions, their application to neural network learning remains unclear. This study proposes a two-level training framework designed to train a bottom-up network using a Top-Down Credit Assignment Network (TDCA-network). The TDCA-network serves as a substitute for the conventional loss function and the back-propagation algorithm, widely used in neural network training. We further introduce a brain-inspired credit diffusion mechanism, significantly reducing the TDCA-network's parameter complexity, thereby greatly accelerating training without compromising the network's performance.Our experiments involving non-convex function optimization, supervised learning, and reinforcement learning reveal that a well-trained TDCA-network outperforms back-propagation across various settings. The visualization of the update trajectories in the loss landscape indicates the TDCA-network's ability to bypass local minima where BP-based trajectories typically become trapped. The TDCA-network also excels in multi-task optimization, demonstrating robust generalizability across different datasets in supervised learning and unseen task settings in reinforcement learning. Moreover, the results indicate that the TDCA-network holds promising potential to train neural networks across diverse architectures.

翻译：尽管基于反向传播算法的深度神经网络已得到广泛应用，但反向传播算法的生物不可信性可能制约新型深度神经网络模型的发展。为寻找可替代反向传播算法的生物可信算法，本研究聚焦于生物大脑固有的自上而下机制。虽然生物大脑中的自上而下连接在高层次认知功能中发挥关键作用，但其在神经网络学习中的应用仍不明确。本文提出一种双层训练框架，通过自上而下信用分配网络（TDCA-network）训练自下而上网络。TDCA-network替代了神经网络训练中广泛使用的传统损失函数与反向传播算法。我们进一步引入脑启发的信用扩散机制，显著降低了TDCA-network的参数复杂度，在不影响网络性能的前提下大幅提升训练速度。在非凸函数优化、监督学习与强化学习中的实验表明，训练完善的TDCA-network在多种设置下均优于反向传播算法。损失景观中更新轨迹的可视化显示，TDCA-network能够绕过基于反向传播算法轨迹常陷入的局部极小值。该网络在多任务优化中同样表现卓越，在监督学习的不同数据集与强化学习的未见任务设置中展现出强大的泛化能力。此外，研究结果表明TDCA-network在训练不同架构的神经网络方面具有广阔前景。