Learning and Teaching Data Science using nanoHUB’s Cloud Resources

By Alejandro Strachan

Network for Computational Nanotechnology, Purdue University, West Lafayette, IN

Published on

Abstract

This talk will discuss how data science is accelerating innovation in STEM fields. These tools enable the efficient handling of valuable data, the identification of patterns in large data collections, the development of predictive models, and the optimal design of experiments. I will show examples from the field of materials science where tools can speed up the discovery and optimization of new materials and reduced the associated cost. The fast adoption of data science in STEM applications calls for an equally fast incorporation of these material in undergraduate and graduate education.In the second part of the talk, I will introduce data science and cloud computing resources in nanoHUB, an open cyberinfrastructure for cloud scientific computing that seeks to maximize the impact of simulations and data in education and research. A hands-on tutorial will introduce participants to modern tools to manage, organize, and visualize data as well as machine learning techniques to model data and make decisions. We will discuss learning modules designed to introduce students and researchers to the fundamentals as well as resources for advanced practitioners.

Bio

Alejandro Strachanis a Professor of Materials Engineering at Purdue University, Director, DoD ONR MURI “Predictive Chemistry and Physics at Extreme Conditions”, PCP@Xtreme, and the Deputy Director of NSF’s nanoHUB. Before joining Purdue, he was a Staff Member in the Theoretical Division of Los Alamos National Laboratory and worked as a Postdoctoral Scholar and Scientist at Caltech. He received a Ph.D. in Physics from the University of Buenos Aires, Argentina. Prof. Strachan’s research focuses on the development of predictive atomistic and multiscalemodels to describe materials from first principles and their combination with data scienceto address problems of technological or scientific importance. Areas of interest include: high-energy density and active materials, metallic alloys for high-temperature applications, materials and devices for nanoelectronics and energy, as well aspolymers and their composites. In addition, Strachan’s scholarly work includes cyberinfrastructure to maximize the impact of and democratize access to models and data for research and education. Prof. Strachan has published over 180 peer-reviewed scientific papers and his contributions to research and education have beenrecognized byseveral awards, including the Early Career Faculty Fellow Award from TMS in 2009, his induction as a Purdue University’s Faculty Scholar (2012-2017), and the R&D 100 award in the area of software and services for nanoHUB.

Sponsored by

University of Puerto Rico

Cite this work

Researchers should cite this work as follows:

  • Alejandro Strachan (2022), "Learning and Teaching Data Science using nanoHUB’s Cloud Resources," https://nanohub.org/resources/35958.

    BibTex | EndNote

Tags

Learning and Teaching Data Science using nanoHUB’s Cloud Resources
  • Learning and teaching data science using nanoHUB's cloud resources 1. Learning and teaching data sci… 0
    00:00/00:00
  • Data Science & Machine Learning 2. Data Science & Machine Learnin… 18.084751418084753
    00:00/00:00
  • Data Science & Machine Learning 3. Data Science & Machine Learnin… 132.0653987320654
    00:00/00:00
  • Data Science & Machine Learning in Science & Engineering 4. Data Science & Machine Learnin… 217.58425091758426
    00:00/00:00
  • Supervised learning 5. Supervised learning 421.95528862195533
    00:00/00:00
  • Supervised learning: regression 6. Supervised learning: regressio… 582.04871538204873
    00:00/00:00
  • Neural networks 7. Neural networks 666.73340006673345
    00:00/00:00
  • Unsupervised learning 8. Unsupervised learning 879.07907907907907
    00:00/00:00
  • Machine learning in engineering 9. Machine learning in engineerin… 1077.5775775775776
    00:00/00:00
  • Maximizing Li+ conductivity in solid oxides 10. Maximizing Li+ conductivity in… 1194.3943943943943
    00:00/00:00
  • Find the best conductor with the fewest experiments 11. Find the best conductor with t… 1242.308975642309
    00:00/00:00
  • Sequential Learning tool in nanoHUB 12. Sequential Learning tool in na… 1358.7253920587254
    00:00/00:00
  • Finding best conductor with the fewest experiments 13. Finding best conductor with th… 1809.4094094094096
    00:00/00:00
  • Join the nanoHUB community 14. Join the nanoHUB community 1917.5508842175509
    00:00/00:00
  • nanoHUB: making simulation & data pervasive 15. nanoHUB: making simulation & d… 1936.67000333667
    00:00/00:00
  • nanoHUB: a community-driven resource 16. nanoHUB: a community-driven re… 2031.2312312312313
    00:00/00:00
  • Hands-on Data Science & Machine Learning Training Series 17. Hands-on Data Science & Machin… 2068.068068068068
    00:00/00:00
  • Learning modules 18. Learning modules 2112.7794461127796
    00:00/00:00
  • Publish for reproducibility and discoverability 19. Publish for reproducibility an… 2171.0043376710046
    00:00/00:00
  • Thanks & Q&A 20. Thanks & Q&A 2209.0090090090089
    00:00/00:00