4 papers
CNet: A Complex-Valued Deep Learning Framework with Wirtinger Autodifferentiation and FFT--Hadamard Convolution
Marcel Crasmaru
CNet is a C++/CUDA framework for building deep complex-valued neural networks (CVNNs) and optimizing complex functions by gradient descent with Wirtinger derivatives. Complex model…
Searching for Primes: A Neural AlphaZero Approach to a Factoring Game
Marcel Crasmaru
We study a one-player token game on an board where tokens slide along diagonals or duplicate onto neighbouring ones to form a combinatorial rectangle . A con…
Two-Thread Coverage MCTS for SAT and XSAT
Marcel Crasmaru
We introduce a Monte-Carlo Tree Search solver for SAT and XSAT that pairs WalkSAT-style rollouts with a two-thread symmetry-breaking initialisation: one thread starts from all-true…
On the Equivalence of Convolutional and Hadamard Networks using DFT
Marcel Crasmaru
In this paper we introduce activation functions that move the entire computation of Convolutional Networks into the frequency domain, where they are actually Hadamard Networks. To…