Supervised learning in artificial neural networks typically relies on backpropagation, where the weights are updated based on the error-function gradients and sequentially propagated from the output layer to the input layer. Although this approach has proven effective in a wide domain of applications, it lacks biological plausibility in many regards, including the weight symmetry problem, the dependence of learning on non-local signals, the freezing of neural activity during error propagation, and the update locking problem. Alternative training schemes have been introduced, including sign symmetry, feedback alignment, and direct feedback alignment, but they invariably rely on a backward pass that hinders the possibility of solving all the issues simultaneously. Here, we propose to replace the backward pass with a second forward pass in which the input signal is modulated based on the error of the network. We show that this novel learning rule comprehensively addresses all the above-mentioned issues and can be applied to both fully connected and convolutional models. We test this learning rule on MNIST, CIFAR-10, and CIFAR-100. These results help incorporate biological principles into machine learning.

翻译：人工神经网络中的监督学习通常依赖于反向传播，其中权重根据误差函数梯度进行更新，并从输出层顺序传播至输入层。尽管该方法在广泛的应用领域已被证明有效，但在许多方面缺乏生物学合理性，包括权重对称问题、学习对非局部信号的依赖、误差传播过程中神经活动的冻结以及更新锁定问题。已有替代训练方案被提出，包括符号对称、反馈对齐和直接反馈对齐，但这些方案无一例外地依赖反向传播，从而阻碍了同时解决所有问题的可能性。本文提出用第二次前向传播替代反向传播，其中输入信号根据网络误差进行调制。研究表明，这种新型学习规则全面解决了上述所有问题，并可应用于全连接和卷积模型。我们在MNIST、CIFAR-10和CIFAR-100上测试了该学习规则。这些结果有助于将生物学原理融入机器学习。