<ul><li>The paper introduces a new learning method named NoProp, which does not rely on either forward or backward propagation in deep learning.</li><li>NoProp takes inspiration from diffusion and flow matching methods to independently learn to denoise a noisy target at each layer.</li><li>The method demonstrates superior accuracy, ease of use, and computational efficiency compared to other back-propagation-free methods on image classification benchmarks such as MNIST, CIFAR-10, and CIFAR-100.</li><li>NoProp alters the traditional gradient-based learning paradigm, enabling more efficient distributed learning and potentially impacting other characteristics of the learning process.</li></ul>

NoProp: Training Neural Networks without Back-propagation or Forward-propagation

Discover more