Subspace Rotation Algorithm for Training Restricted Hopfield Network

This paper introduces the Subspace Rotation Algorithm (SRA) for training the Restricted Hopfield Network (RHN) as an auto-associative memory. SRA is a gradient-free subspace tracking method based on Singular Value Decomposition (SVD) to update the weight matrix. Despite having slightly worse time complexity than Back-propagation (BP) theoretically, in practice, SRA completes training faster since it requires fewer iterations to converge. Comparative analysis with BP for training RHN reveals that SRA consistently reaches the optimal solution, whereas BP fails to achieve comparable performance if the weight initialization is not within the appropriate basin of attraction. Experiments involving the memorization of 10, 50, and 100 patterns from the MNIST dataset show that RHN trained with SRA exhibits better robustness to noisy and corrupted patterns compared to RHN trained with BP. These findings suggest that SRA offers a more reliable and effective method for training RHNs in applications needing high tolerance to input distortions.