Detail of the student project

Topic:Sudoku solver učený z příkladů
Department:Katedra kybernetiky
Supervisor:Ing. Vojtěch Franc, Ph.D.
Announce as:Diplomová práce, Bakalářská práce, Semestrální projekt
Description:Design a program that will learn solver of the Sudoku puzzle from examples of Sudoku assignments and (possibly partial) solutions. The assignment can be either symbolic or visual, i.e. given as an image of the puzzle. Compare your solution to common network architectures trained to solve the problem in end-to-end fashion.
Bibliography:- Franc, Prusa, Yermakov. Consistent and Tractable Algorithm for Markov Network learning. ECML 2022.
- Wang, P., Donti, P., Wilder, B., Kolter, J.: SATnet: Bridging deep learning and logical reasoning using a differential satisfiability solver. In: ICML (2019)
Responsible person: Petr Pošík