2 papers
cs.IT2026
Derandomizing Dense Binary Hypervector Codebooks for Quantized Scalars
Dmitri Rachkovskij, Evgeny Osipov, Olexander Volkov +2
Hyperdimensional computing and vector symbolic architectures often represent quantized scalar levels by dense binary codebooks whose level-to-level similarity is intended to follow…
cs.LG2026
Multiclass Linear Perceptrons with Multiplicative Margins
Dmitri Rachkovskij, Evgeny Osipov, Olexander Volkov +2
This paper introduces a family of multiclass linear Perceptron classifiers with a multiplicative margin mechanism (MMPerc), as an alternative to standard margin-free and additive m…