Kernel Logistic Regression Learning for High-Capacity Hopfield Networks
This addresses a fundamental bottleneck in associative memory models for AI and neuroscience, offering a significant improvement over existing methods.
The paper tackled the limited storage capacity of Hopfield networks by proposing Kernel Logistic Regression learning, which achieved perfect recall with pattern-to-neuron ratios up to 1.5 and improved noise robustness.
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 learning dual variables, KLR dramatically improves storage capacity, achieving perfect recall even when pattern numbers exceed neuron numbers (up to ratio 1.5 shown), and enhances noise robustness. KLR demonstrably outperforms Hebbian and linear logistic regression approaches.