Data Science for Engineers
This series of intensive courses is designed to help practicing engineers harness the power of data in their work to achieve results.
The Autumn 2021 section of DSFE (October – November) is postponed and future dates will be announced soon.
Optimize Workflows and Improve Business Decisions with Data
To be effective and keep up to speed in today’s workforce, engineers need to understand how to efficiently manage, process, and respond to an ever-expanding stream of data from industrial sensors, robotics and advanced instrumentation. Data Science for Engineers participants learn to apply data science and machine learning methods to transform raw data and uncover valuable, actionable insights within their organizations.
Learn How To
Designed for Insight, Not Just Completion
Data Science for Engineers was custom-built in conjunction with University of Washington’s Chemical Engineering faculty to give working professionals advanced data science skills pertinent to their roles and needs. In this university-level course, attendees learn collaboratively alongside peers, industry speakers, and a member of the UW faculty – exploring common challenges, studying real use cases, and applying learnings to their own data in real time. More than a generic series of tutorials, Data Science for Engineers gives participants the tools and consulting necessary to provide actionable insights and immediate, hyper-relevant applications.
Who Should Enroll
This course series is designed for working chemical and process engineers interested in optimizing and automating plant operations or developing data-driven strategies for their business. Each course can be taken individually or taken together as a linked series. Participants in individual courses will focus on specific topics and earn 2 Continuing Education Units (CEUs) per course. When taking the series, topics build and participants earn 6 CEUs. Series participants can also receive 6 transcriptable credits from the University of Washington.
Enroll in the series if you intend to apply data science tools in your work on a regular basis and would like to build a robust working model with ongoing faculty consultation using your own dataset or one provided.
Visit the More Information page for answers to frequently asked questions and information on transcriptable credit.
What You Will Learn
Participants in this series will learn how to apply fundamental programming skills and modern data science methods with real data sets and models. Participants will understand the opportunities and constraints of working with large data sets to improve automation, optimization, and strategic decision making that benefit operations and the business, overall.
Topics include:
- Exploratory data analysis
- Supervised and unsupervised machine learning models
- Neural networks and introduction to AI
- Effective data dashboarding
Case studies introduce concepts and a complex simulation of a factory, or surrogate model, provide a through-line for all three courses in the series, which will help you to apply concepts and explore ways to optimize both a wide range of business processes and operations.
At the conclusion of the series, participants will be able to confidently manage complex sets of data and use them to predict and model processes, automate tasks, reduce downtime, improve margin velocity, enable line and product level consolidation, reduce changeover, and other means of optimization that have a direct impact on your company’s bottom line.
This series is equivalent to University of Washington’s Chemical Engineering courses UW CHEM E 545 & 546 — courses developed as part of a $3 million investment in creating unique graduate level coursework at the intersection of data science and chemical engineering.
Data Science for Engineers Schedule
Course 1: Build Your Base
-
Topics Covered
• Introduction to Python
• Lists, dictionaries, and flow control
• Functions and Pandas data frames
• Visualization: Matplotlib, Seaborn, and Pandas
• Supervised learning: regression -
Case Studies
• Importing, cleaning, and visualizing process data
• Correlating inputs and feature engineering of process data -
Course Prerequisites
None. This course assumes zero knowledge of Python.
Course 2: Model Your Process
-
Topics Covered
• Importing, cleaning, and visualizing process data
• Correlating inputs and feature engineering of process data -
Case Studies
• Populating missing data fields
• Predictive equipment maintenance -
Course Prerequisites
Course 1, or a working knowledge of Python and familiarity with the Python data analysis stack: Pandas, NumPy, Matplotlib, and SciPy.
Course 3: Leverage Your Model
-
Topics Covered
• Multilayer Perceptrons
• Feed-forward neural networks
• Convolutional neural networks
• Statistical hypothesis testing
• Time series data modeling
• Data dashboards in Colab and Jupyter -
Case Studies
• Optimizing product margin and margin velocity
• Assessing asset performance and process variability: rate, yield, and uptime
• Consolidating products and lines
• Detecting product defects -
Course Prerequisites
Course 1 & 2, or a working knowledge of common machine learning frameworks including supervised and unsupervised learning models; understanding of rudimentary statistical analysis.
Meet the Instructor
Dr. Beckner is a GIX faculty member, an instructor for the UW MS in Technology Innovation, a Data Science Advisor for the Pfaendtner Research Group, and partner at MFG Analytic, where he works with manufacturing clients to optimize their production processes using cloud-based tools. He received his Ph.D. in Chemical Engineering Data Science from the University of Washington and his B.S. in Chemical Engineering from the University of Texas at Austin. His consulting work inspired him to help organizations streamline their workflows and increase profit margins by training in-house employees to better understand and use data. In this course series, he distills his knowledge as a chemical engineering data scientist to the most salient, practical information applicable to the practicing engineer. Read his full biography here.
Course Details & Registration
Format
Each online course in the Data Science for Engineers series is 4 days long from 8:00 a.m. - 2:00 p.m. (PST) with a break for lunch. Instruction is virtual.
Price
Each course in the series is $2500. Participants that register for the full series will receive a 15% discount.
David Hurt, Battery Technology consulting engineer
Explore Other Programs
Delivering Innovation in a Distributed Team
Gain critical, actionable tools that will improve your distributed team’s ability to perform, innovate, and collaborate remotely
Data Science for Business
This intensive course is designed for managers who want a better grasp of data science, AI, and machine learning to inform decisions, business strategies, and interactions with data science professionals and consultants