Artificial Intelligence and High Performance Computing Journal Club seminar series
The AI/HPC Journal Club will hold a seminar on Friday, Dec. 6, 2019, at 10 a.m. in Building 241, Room D172. Join us for a presentation by Ganesh Sivaraman (LCF).
“Materials Science Driven by Simulation, Data, and Learning “
A large corpus of material and experimental data exists in historic scientific literature. Natural language processing and data-mining approaches can be applied to curated scientific literature to extract chemical information for targeted functionality and applications. The first half of this talk focuses on development of a UV/vis absorption spectra database by means of a complex quantum chemistry workflow built on the top of the ChemDataExtractor tool by leveraging DOE Argonne leadership computing facilities as a part of the data science project allocation. I will discuss the results of retrieving chemical information and experimental properties from a large sample of scientific literature ( 400,000) with chemdataextractor.
In the second part of the talk, I will discuss a novel application of graph neural network and state of the art generative model based on the SELFIES representation applied to drug like molecules.
Interested in joining the mailing list or presenting in the seminar series?
We are Argonne’s Artificial Intelligence & High Performance Computing (AI & HPC) Seminar Series, formerly known as the “Machine Learning (ML) & HPC Journal Club.
Objectives of the AI & HPC seminar series:
1. To form a community that brings both ML/AI/HPC experts and domain scientists together for AI’s applications in science.
2. To introduce latest AI developments and applications.
3. To create a platform to communicate technical and theoretical aspects of AI research across the laboratory.
4. To encourage open discussions and sharing for researchers at all levels.
5. To provide a database of ML/AI resources for interested members of the laboratory (via a shared Box folder).
Join the seminar on BlueJeans.