Improving Predictive Uncertainty Estimation using Dropout -- Hamiltonian Monte Carlo

no code implementations • 12 May 2018 • Diego Vergara, Sergio Hernández, Matias Valdenegro-Toro, Felipe Jorquera

Estimating predictive uncertainty is crucial for many computer vision tasks, from image classification to autonomous driving systems.

Autonomous Driving Bayesian Inference +2

General Algorithmic Search

no code implementations • 24 May 2017 • Sergio Hernández, Guillem Duran, José M. Amigó

In this paper we present a metaheuristic for global optimization called General Algorithmic Search (GAS).

Optimization and Control 90C26