Advances on Active Learning for Efficient Global Optimization of Atomic Clusters
Detalhes
- Tipo de apresentação: Apresentação Oral Síncrona / Synchronous Oral Communication
- Eixo temático: Desenvolvimento e/ou Implementação de Método/Teoria
- Palavras chaves: Machine Learning; Bayesian optimization; Active learning; Global optimization;
- 1 Universidade Federal do Espírito Santo, Brazil
- 2 University of Calgary
- 3 Departamento de Química / CINVESTAV
- 4 National Research Council of Canada
Advances on Active Learning for Efficient Global Optimization of Atomic Clusters
Maicon Lourenço
Universidade Federal do Espírito Santo, Brazil
Resumo
In this work, we will discuss the progress of the QMLMaterial software for efficient global optimization (GO) of atomic cluster and/or spin multiplicity (SM) by means of the active learning (AL) method. The method was applied for the GO of Na20 and 3Al@Si11 atomic clusters. The local optimization of the structures was done using SCC-DFTB and DFT, respectively. For the 3Al@Si11, the doped configurations and the SMs (2, 4, 6) were considered during the search. The Gaussian Process (GP) and Neural Network (NN) algorithms were used with the MBTR structural descriptor in the proposed method.
Discussões Científicas de Qualidade
Com ~200 mil publicações revisadas por pesquisadores do mundo todo, o Galoá impulsiona cientistas na descoberta de pesquisas de ponta por meio de nossa plataforma indexada.
Confira nossos produtos e como podemos ajudá-lo a dar mais alcance para sua pesquisa:
