Thinking through.

Danilo Naiff's personal website.

About

drawing

Hi, I’m Danilo Naiff, and this is a personal website of mine where I share some personal writings, mainly technical ones on deep learning, although I delve into other topics as well.

Bio

Danilo Naiff is a Materials Engineer and holds a Master’s degree in Mathematics from the Federal University of Rio de Janeiro. He is currently pursuing a Ph.D. in Mechanical Engineering at the Federal University of Rio de Janeiro. His main line of work involves using machine learning for various scientific applications. Currently, he focuses on the use of generative models for generating porous media and predicting ocean currents. Additionally, he has worked in radioactive field dose estimation, calcium carbonate fouling, and solutions to finance equations, among other areas.

Danilo is also involved with the Effective Altruism community in Brazil, with a particular interest in AI Safety. He has participated in programs such as the AI Safety Camp, AI Safety Fundamentals, and the first phase in SERI MATS. He is now actively mentoring in various AI alignment programs in Brazil.

Github
Linkedin
Google Scholar

Research

Papers

  1. Ali Al‑Aradi, Adolfo Correia, Gabriel Jardim, Danilo de Freitas Naiff and Yuri Saporito, Extensions of the deep Galerkin Method, Applied Mathematics and Computation, 2022.
  2. Paulo R. Silveira, Danilo de F. Naiff, Claudio M.N.A. Pereira, Roberto Schirru Reconstruction of radiation dose rate profiles by autonomous robot with active learning and Gaussian process regression, Annals of Nuclear Energy, 2018

Reports

  1. Ali Al‑Aradi, Adolfo Correia, Danilo de Freitas Naiff, Gabriel Jardim, and Yuri Saporito, Solving Nonlinear and High‑Dimensional Partial Differential Equations via Deep Learning, 2020

Pre-prints

  1. Gabriel Sanfins, Fabio Ramos, Danilo Naiff, Similarity Learning with neural networks.
  2. Danilo Naiff, Shashwat Goel, Low Impact Agency: Review and Discussion, 2023.
  3. Ali Al‑Aradi, Adolfo Correia, Danilo de Freitas Naiff, Gabriel Jardim, and Yuri Saporito, Applications of the deep Galerkin method to solving partial integro‑differential and Hamilton—Jacobi–Bellman equations, 2018

Others

  1. Simon Fischer, benjaminko, jazcarretao, DFNaiff, Jeremy Gillen, AISC team report: Soft‑optimization, Bayes and Goodhart, LessWrong, 2022.