MLflow is an incredible open-source tool that offers excellent solutions to tracking each iteration of machine learning application, comparing each run, then packaging up the top-performing model and implementing the model. This tool reinforces model development best practices and provides excellent, easily implemented support. In this tutorial, we will review model development best practices, then spend time implementing MLflow with hands-on practice of the open-source tools.

Speaker: Mary Willcock


Coming from a non-traditional background, Mary worked in the financial industry for ten years prior to continuing her education at Northwestern University with a Master’s degree in Data Science specializing in Analytics and Modeling. As a Data Scientist, Mary has worked in the Education Technology and Retail industries and now at Talavant Mary is building the data science part of the consultant practice and gaining experience in a wide variety of industries and projects. Mary values effective solutions that can make a real difference in the way business is run. With a passion for learning, Mary works to stay at the forefront of data science, always learning more about implementing AI techniques and building an organization from hindsight to foresight through data.

The performance of machine learning approaches is heavily dependent on the choice and quality of data representation. Deep learning is part of a broader family of machine learning methods based on learning meaningful and effective data representations, as opposed to feature engineering. This tutorial aims to provide a path for a deep neural networks newcomer to gain some understanding of this vast and complex topic. To facilitate a real understanding of deep learning, basic machine learning theory and concepts will also be covered to some degree. Finally, we will present some interesting applications of deep learning in speech and image analysis, developed in Machine Vision and Pattern Recognition Lab. at Wayne State University.

Speaker: Dr. Ming Dong


Ming Dong received his B. S. degrees in electrical engineering and industrial management engineering from Shanghai Jiao Tong University, Shanghai, China, in 1995. He received his Ph. D degree in electrical engineering from University of Cincinnati in 2001. He is currently a professor in the Department Computer Science and the co-director of the Data Science and Business Analytics program and the Big Data & Business Analytics Group at Wayne State University. He is also the director of the Machine Vision and Pattern Recognition Lab. Dr. Dong’s areas of research include deep learning, data mining, and computer vision with applications in health informatics and automotive industry. His research is funded by National Science Foundation, National Institutes of Health, State of Michigan, Private Foundations (e.g., Michigan Health Endorsement Fund, Epilepsy Foundation) and Industries (e.g., APB Investment, Ford Motor Company). He has published over 100 technical articles in premium journals and conferences in related fields, e.g., TMM, TPAMI, TKDE, TNN, TVCG, TC, IEEE CVPR, IEEE ICCV, IEEE ICDM, ACM MM, AMIA and WWW. He is/was an associate editor of Statistical Analysis and Data Mining, the American Statistical Association (ASA) Data Science Journal (since 2018), Journal of Smart Health (Since 2016), IEEE Transactions on Neural Networks (2008-2011), and Pattern Analysis and Applications (2007-2010), and served in many conference program committees and US National Science Foundation panels. He also served as senior research consultant in Baidu Inc. in 2008.

All enterprises want to be data-driven, however, most businesses seem to struggle with the basics. This introductory hands-on workshop will expose the audience to basic best practices on how to deep-dive into data sets, exploit traditional databases, apply basic machine learning and AI methods, and analyze trends for business insights. Participants will receive instructions around any necessary software installation in advance of the workshop to come prepared for the hands-on activities.

Speaker: Adam Yatooma

Adam is a Customer Engineer with the Google Cloud Platform team and helps customers transform and evolve their business through the use of Google’s global network, web-scale data centers and software infrastructure. He has over a decade of experience in software consulting and sales.

Learn why the truly open source HPCC Systems platform is Better at Big Data and learn how ECL can empower you to build powerful data queries all while indulging your passion for music. Anyone who needs a basic familiarity of the platform and wants to learn best practices with the easy to learn, declarative ECL language should attend. This workshop will take the student through the data extraction, transformation and delivery cycle using HPCC Systems and ECL. Code examples and hands-on lessons will be included. A public dataset based on the Million Song Dataset and other auxiliary data will be used.

Class Prerequisites – Bring your laptop for this hands-on learning workshop: Course includes thumb drive which included data, code and documentation as well as connection to an AWS cluster.

Speaker: Bob Foreman


Bob Foreman has worked with LexisNexis and the open source big data HPCC Systems technology platform and the ECL programming language for more than 9 years, and has been a technical trainer for more than 25 years. He is the developer and designer of the HPCC Systems Online Training Courses, and is the Senior Instructor for all classroom and remote training. This includes: Introduction to ECL (Part 1 and 2) – Concepts and Queries, the Extract, Transform and Load (ETL) Process, Advanced ECL (Part 1 and 2) – Working with Relational Data, Super files, Working with XML, and Free-form Text Parsing, ROXIE ECL – Indexes and Queries, Complex Query Development, and Applied ECL – ECL Code Generation Tools.