Aldair E. Gongora

TL;DR: A Bayesian experimental autonomous researcher (BEAR) that combines Bayesian optimization and high-throughput automated experimentation that explores the toughness of a parametric family of structures and observes an almost 60-fold reduction in the number of experiments needed to identify high-performing structures relative to a grid-based search.

TL;DR: In this paper, the authors evaluate the performance of active learning algorithms such as Bayesian optimization (BO) for general materials optimization and find that for surrogate model selection, Gaussian Process (GP) with anisotropic kernels (automatic relevance detection, ARD) and Random Forests (RF) have comparable performance and both outperform the commonly used GP without ARD.

TL;DR: In this article, the authors investigate whether imperfect data from simulation can accelerate autonomous experimentation using a case study on the mechanics of additively manufactured structures, and highlight multiple ways that simulation can improve AE through transfer learning.

TL;DR: In this paper, the authors reviewed the state of bagasse cogeneration in Belize and assessed its potential for further expansion, and explored the expansion of co-generation energy technologies to increase local energy generation output to the national grid.

TL;DR: In this article , a transfer learning approach was developed to determine how more widely available quasi-static testing can be used to predict impact protection, and the transferability of this model using a distinct family of lattices was evaluated using automated mechanical testing.