no code implementations • NeurIPS Workshop AI4Scien 2021 • Sean Hooten, Sri Krishna Vadlamani, Raymond G. Beausoleil, Thomas Van Vaerenbergh
A generative neural network based non-convex optimization algorithm using a one-step implementation of the policy gradient method is introduced and applied to electromagnetic design.
no code implementations • 30 Jun 2021 • Sean Hooten, Raymond G. Beausoleil, Thomas Van Vaerenbergh
We present a proof-of-concept technique for the inverse design of electromagnetic devices motivated by the policy gradient method in reinforcement learning, named PHORCED (PHotonic Optimization using REINFORCE Criteria for Enhanced Design).
no code implementations • 18 Dec 2020 • Fabian Böhm, Thomas Van Vaerenbergh, Guy Verschaffelt, Guy Van der Sande
By simulating Ising machines with polynomial, periodic, sigmoid and clipped transfer functions and benchmarking them with MaxCut optimization problems, we find the choice of transfer function to have a significant influence on the calculation time and solution quality.
Applied Physics Emerging Technologies Computational Physics
no code implementations • 30 Sep 2015 • Michiel Hermans, Thomas Van Vaerenbergh
In this paper we study the concept of using the interaction between waves and a trainable medium in order to construct a matrix-vector multiplier.