Dr. Daniel C. Elton

Daniel C. Elton, Ph.D. is a Staff Scientist at the National Institutes of Health, where he works on research for applications of artificial intelligence and deep learning to enable computer-aided diagnosis and detection in medical images in Diagnostic Radiology Department.

Before joining the NIH in 2019, Dan was Assistant Research Scientist at the University of Maryland, College Park, where he focused on applying machine learning methods to molecular property prediction and molecular design.

Dan demonstrated for the first time that machine learning models can predict the properties of explosive materials with high accuracy and low computational cost and how sensitivity analysis of machine learning models and feature ranking techniques can be used to help discover relationships between molecular structures and properties.

While at the University of Maryland, he was also a part of the IDEAL Lab team, where his work focused on applying machine learning methods to molecular property prediction and molecular design and wrote a review article on Deep Learning Architectures for molecular generation and demonstrated how a generative adversarial network can be used to generate sets of potentially useful molecules, and also helped to explain the utility of machine learning methods to program managers and chemists in DoD agencies.

Prior to becoming an Assistant Research Scientist, Dan was Postdoctoral Associate in the Mechanical Engineering Department between 2017 and 2018. He was chosen as one of 36 talents out of hundreds of applicants to participate in the Mindfire Global program in Davos, Switzerland. Mindfire is a new initiative that brings together top talents in artificial intelligence, neuroscience, and other fields to help develop novel biologically inspired approaches to AI.

Dan earned his Ph.D. in Physics from Stony Brook University in 2016 with his thesis Understanding the Dielectric Properties of Water. He was a Graduate Research Assistant since 2012, with his Ph.D. advisor Prof. Marivi Fernández-Serra. Among all his work, the most notable was planning and executing a detailed study of the dielectric properties of water which led to the discovery of optical phonon-like modes in liquid water. After his Ph.D., Dan became a STEM Tutor in the Learning Center at Schenectady County Community College. He mostly tutored Physics, Chemistry, and Mathematics.

Dan earned his Bachelor’s Degree of Science in Physics from Rensselaer Polytechnic Institute, New York in 2009. He was an Undergraduate Research Assistant from 2008, and Graduate Teaching Assistant until 2010.

In the summer of the same year, he did his Summer Undergraduate Laboratory Internship (SULI) at Los Alamos National Laboratory, where he worked with Dr. Garrett Kenyon on biologically-inspired neural networks for computer vision.

Dan has written a number of publications and peer reviewed journal articles, among others:

• Deep learning for molecular design — a review of the state of the art, 2019
• Applying machine learning techniques to predict the properties of energetic materials, 2018
• The hydrogen-bond network of water supports propagating optical phonon-like modes, 2016

Besides Physics, Machine Learning, and Technological Progress, Dan also likes to write about Music, Art, and other daily life subjects. He was also a founder and organizer of the Tech Valley Machine Learning, Data Science, and AI meetup.

Visit his Website, LinkedIn profile, H+Pedia profile, ResearchGate profile, Wikipedia page, Kaggle page, Publons page, Semantic Scholar page, and Google Scholar page. Follow him on Facebook, Loop, Quora, GitHub, SlideShare, and Twitter.