ON-DEMAND WEBINAR
From Modelling to Deep Learning: Advanced Image and Text Analysis
Do you collect image and/or unstructured text data as part of your research, development, or production activities? Are you finding manual analysis of such unstructured data to be difficult, tedious, or error-prone?
You’ve spent valuable time and effort collecting your data sets, and now want to put them to constructive use. You are therefore interested in reliably recognizing patterns from your images or the text responsible for these defects – and doing so in a timely manner.
In this webinar, we introduce some novel ways to analyze image and text data to aid in classifying, predicting, and improving performance using deep learning methods that are simple to apply and master. The machine learning and modeling techniques within JMP Pro are powerful for analyzing tabular or spreadsheet data common in R&D and manufacturing. A new add-in for JMP Pro allows users to extend this functionality to deep learning and AI models capable of image and text analysis. Using case studies, you can transform your data into meaningful insights, thus achieving better outcomes.
Case studies include:
- Predicting molecular properties from SMILES strings.
- Predicting defects from wafer map images.
- Predicting sentiment from product reviews.
- Predicting relevance from scientific titles and abstracts.
This webinar should interest anyone working in research, development, or production who is collecting unstructured data and hoping to make better use of it.
After this webinar, you'll have a better understanding of what is possible with modern and easy-to-apply deep learning methods so you can make better decisions from your unstructured data.
About the Presenters
David Barnett, Formulation Design Chemist, Syngenta
David Barnett is Senior Formulation Chemist, Data Scientist and Robotics Chemist for Syngenta Crop Protection at its Jealott’s Hill R&D site near Reading in the UK.
Russ Wolfinger, Director of Scientific Discovery and Genomics, JMP
Russ Wolfinger, PhD, is the Director of Scientific Discovery and Genomics at JMP Statistical Software LLC, a SAS company specializing in interactive desktop software for dynamic data visualization and analysis.
In this role, Russ leads a team in research and development of JMP-based software solutions in the life sciences. He joined SAS in 1989 after earning a PhD in Statistics from North Carolina State University (NCSU). For ten years he devoted his efforts to developing and promoting statistical procedures for mixed models and multiple testing. In 2000 he started the Scientific Discovery department at SAS and JMP.
Russ is co-author of more than 150 publications, 4 books, and is the most cited author at SAS. He is a fellow of both the American Association for the Advancement of Science and the American Statistical Association, an adjunct faculty member at NCSU and the University of North Carolina at Chapel Hill, and a Kaggle Competition Grandmaster.