Shedding Light on Variational Autoencoders

Autor(es)

Ruiz Vargas, J. C. ; Novaes, S. F. ; Cobe, R. ; Iope, R. ; Stanzani, S. ; Tomei, T. R. ; IEEE

• Tipo de documento: Artigo Científico
• Fonte: 2018 XLIV LATIN AMERICAN COMPUTER CONFERENCE (CLEI 2018); v. N/A, p. 5-pg., 2018-01-01.

Resumo

Deep neural networks provide the canvas to create models of millions of parameters to fit distributions involving an equally large number of random variables. The contribution of this study is twofold. First, we introduce a diffraction dataset containing computer-based simulations of a Young's interference experiment. Then, we demonstrate the adeptness of variational autoencoders to learn diffraction patterns and extract a latent feature that correlates with the physical wavelength. (AU)

• Processo FAPESP: 13/01907-0 - Centro de Pesquisa e Análise de São Paulo
• Beneficiário: Sergio Ferraz Novaes
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 16/15897-4 - Busca por nova física no experimento CMS do Large Hadron Collider
• Beneficiário: Thiago Rafael Fernandez Perez Tomei
• Modalidade de apoio: Auxílio à Pesquisa - Regular