Automatic Generation of Neural Architecture Search Spaces

1 code implementation • AAAI Workshop CLeaR 2022 • David Calhas, Vasco M. Manquinho, Ines Lynce

Here, we propose a framework that encodes the structure of a convolutional neural network, respecting the arithmetical relation of the kernel and stride sizes with the input and output shapes.

Neural Architecture Search

Reflections on "Incremental Cardinality Constraints for MaxSAT"

no code implementations • 10 Oct 2019 • Ruben Martins, Saurabh Joshi, Vasco Manquinho, Ines Lynce

To celebrate the first 25 years of the International Conference on Principles and Practice of Constraint Programming (CP) the editors invited the authors of the most cited paper of each year to write a commentary on their paper.

Incremental Cardinality Constraints for MaxSAT

no code implementations • 20 Aug 2014 • Ruben Martins, Saurabh Joshi, Vasco Manquinho, Ines Lynce

In general, MaxSAT algorithms perform a succession of SAT solver calls to reach an optimum solution making extensive use of cardinality constraints.