Using machine learning clustering to find large coverage holes
Raviv Gal, Giora Simchoni, et al.
MLCAD 2020
In computer aided design (CAD), a core task is to optimize the parameters of noisy simulations. Derivative free optimization (DFO) methods are the most common choice for this task. In this paper, we show how four DFO methods, specifically implicit filtering (IF), simulated annealing (SA), genetic algorithms (GA), and particle swarm (PS), can be accelerated using a deep neural network (DNN) that acts as a surrogate model of the objective function. In particular, we demonstrate the applicability of the DNN accelerated DFO approach to the coverage directed generation (CDG) problem that is commonly solved by hardware verification teams.
Raviv Gal, Giora Simchoni, et al.
MLCAD 2020
Eldad Haber, Brian Irwin, et al.
ICML 2023
Raviv Gal, Haim Kermany, et al.
DAC 2020
Raviv Gal, Eldad Haber, et al.
Optimization and Engineering