Akira Tamamori

Kernel Logistic Regression Learning for High-Capacity Hopfield Networks

2025 · IEICE Transactions on Information and Systems

Hebbian learning limits Hopfield network storage capacity (pattern-to-neuron ratio around 0.14). We propose Kernel Logistic Regression (KLR) learning. Unlike linear methods, KLR uses kernels to implicitly map patterns to high-dimensional feature space, enhancing separability. By …