Enabling the Next Generation of Data Scientist : Analytics and Machine Learning in Pipeline Pilot
Overview: Not everyone in your organization can be a data scientist. Pipeline Pilot’s data pipelining architecture and numerous relevant components enable more scientists and engineers to do their own data science. Pipeline Pilot is the industry’s flagship environment for productive analytics, data science, and machine learning. Join us and learn how to effectively be your own data scientist, learn how to collect, aggregate and analyze data sets and to spot trends, which can lead to better organizational decisions. Our data science tools will enable you to apply statistics, modeling, computer science and business analytics to any relevant needs. Learn about applications in molecular design, formulation design, high performance materials, and more.
Target Audience: Scientists, engineers, and IT analysts. Some Pipeline Pilot experience a plus, but not required!
This workshop will show you how to:
Overview: Not everyone in your organization can be a data scientist. Pipeline Pilot’s data pipelining architecture and numerous relevant components enable more scientists and engineers to do their own data science. Pipeline Pilot is the industry’s flagship environment for productive analytics, data science, and machine learning. Join us and learn how to effectively be your own data scientist, learn how to collect, aggregate and analyze data sets and to spot trends, which can lead to better organizational decisions. Our data science tools will enable you to apply statistics, modeling, computer science and business analytics to any relevant needs. Learn about applications in molecular design, formulation design, high performance materials, and more.
Target Audience: Scientists, engineers, and IT analysts. Some Pipeline Pilot experience a plus, but not required!
This workshop will show you how to:
- Clean your data sets
- Characterize the variables in a data set and their relationships
- Master different machine learning algorithms like Bayesian, Random Forest, Linear Discrimination Analysis, Support Vector Machines, GFA and more….
- Build and validate a variety of predictive models
- Apply your models to make new predictions and optimizations.
