April 7, 2020
Training offered by nanoHUB to jump-start data science and machine learning
While many researchers and educators may be experiencing restricted access to labs during the COVID-19 crisis, nanoHUB, a premier open and free platform at Purdue for computational research, education and collaboration, is offering a series of open, hands-on tutorials and office hours that will jump-start the use of data science and machine learning in research and teaching.
The series is aimed at active researchers and educators with no prior coding experience. All exercises use nanoHUB cloud computing resources, so there is no need to download or install any software. All that is needed is an internet connection and a browser.
After the training sessions, participants will be able to continue to use nanoHUB for their research or class. Importantly, half of the time in each session will be allotted to Q&A, aiming to provide one-on-one guidance to solve specific problems.
“We hope that you can attend this workshop and walk away with enough information and practical skills to kick-start your foray into machine learning methods for your research or classroom use,” says Ale Strachan, professor of materials engineering and deputy director of nanoHUB.
The workshop is organized in six sessions:
- Session 1: Intro to Jupyter in nanoHUB, Pandas for data organization and plotting.
- Session 2: Repositories and data management.
- Session 3: Supervised learning part 1: linear regression and neural networks.
- Session 4: Supervised learning part 2: classification and random forests.
- Session 5: Unsupervised learning: dimensionality reduction via matrix decomposition.
- Session 6: Sequential learning and design of experiments.
More information and sign-up links are available online.