3 papers
cs.AI2026
Formal Verification of Minimax Algorithms
Wieger Wesselink, Kees Huizing, Huub van de Wetering
Minimax-based search algorithms with alpha-beta pruning and transposition tables are a central component of classical game-playing engines and remain widely used in practice. Despi…
cs.LG2025
Batch Matrix-form Equations and Implementation of Multilayer Perceptrons
Wieger Wesselink, Bram Grooten, Huub van de Wetering +2
Multilayer perceptrons (MLPs) remain fundamental to modern deep learning, yet their algorithmic details are rarely presented in complete, explicit \emph{batch matrix-form}. Rather,…
cs.LG2024
Nerva: a Truly Sparse Implementation of Neural Networks
Wieger Wesselink, Bram Grooten, Qiao Xiao +2
We introduce Nerva, a fast neural network library under development in C++. It supports sparsity by using the sparse matrix operations of Intel's Math Kernel Library (MKL), which e…