Hi [[ session.user.profile.firstName ]]

Converging DOEs and Machine Learning with Self-Validating Ensemble Modeling

Self-Validating Ensemble Modeling (S-VEM) is an exciting, new method that delivers machine learning accuracy to Design of Experiments (DOE) and has many applications in manufacturing and chemical processes.

Machine learning methods are valued because they produce excellent predictive models, but until now they have been disqualified from use with small data sets, including designed experiments, because of the limited amount of data. The limitations have been:
· DoEs could not be validated, so they were less reliable.
· The relationship between the models and the designs were essentially fixed. Expanding the terms in the model and dealing with noisy data required running additional experiments.
· Typically experiments could only accommodate up to second-order parameters, yet the relationships among parameters is typically higher.

S-VEM generates robust, higher-order models that yield greater insights and characterization using considerably fewer runs, thereby saving time and money and reducing risk.

In this talk, we’ll provide an overview of S-VEM as a new, advanced machine learning method, demonstrate a couple of use cases using our new S-VEM analytical product, and suggest how you can explore this method further.

Who Should Attend:

Engineers, scientists and their management who are engaged in research, problem solving and process development and characterization
Recorded Oct 21 2020 58 mins
Your place is confirmed,
we'll send you email reminders
Presented by
Christopher Gotwalt, PhD, SAS Institute | Philip Ramsey, PhD, Predictum Inc. | Wayne Levin, Predictum Inc.
Presentation preview: Converging DOEs and Machine Learning with Self-Validating Ensemble Modeling

Network with like-minded attendees

  • [[ session.user.profile.displayName ]]
    Add a photo
    • [[ session.user.profile.displayName ]]
    • [[ session.user.profile.jobTitle ]]
    • [[ session.user.profile.companyName ]]
    • [[ userProfileTemplateHelper.getLocation(session.user.profile) ]]
  • [[ card.displayName ]]
    • [[ card.displayName ]]
    • [[ card.jobTitle ]]
    • [[ card.companyName ]]
    • [[ userProfileTemplateHelper.getLocation(card) ]]
  • Channel
  • Channel profile
  • Converging DOEs and Machine Learning with Self-Validating Ensemble Modeling Recorded: Oct 21 2020 58 mins
    Christopher Gotwalt, PhD, SAS Institute | Philip Ramsey, PhD, Predictum Inc. | Wayne Levin, Predictum Inc.
    Self-Validating Ensemble Modeling (S-VEM) is an exciting, new method that delivers machine learning accuracy to Design of Experiments (DOE) and has many applications in manufacturing and chemical processes.

    Machine learning methods are valued because they produce excellent predictive models, but until now they have been disqualified from use with small data sets, including designed experiments, because of the limited amount of data. The limitations have been:
    · DoEs could not be validated, so they were less reliable.
    · The relationship between the models and the designs were essentially fixed. Expanding the terms in the model and dealing with noisy data required running additional experiments.
    · Typically experiments could only accommodate up to second-order parameters, yet the relationships among parameters is typically higher.

    S-VEM generates robust, higher-order models that yield greater insights and characterization using considerably fewer runs, thereby saving time and money and reducing risk.

    In this talk, we’ll provide an overview of S-VEM as a new, advanced machine learning method, demonstrate a couple of use cases using our new S-VEM analytical product, and suggest how you can explore this method further.

    Who Should Attend:

    Engineers, scientists and their management who are engaged in research, problem solving and process development and characterization
  • Modernizing Development Practices for Applications that Use JSL Recorded: Jun 3 2020 50 mins
    Vince Faller, Chief Software Engineer, Predictum Inc. and Wayne Levin, President, Predictum Inc.
    This session explores how Predictum’s development team has modernized its development environment for building analytical applications, which are based on JMP software. Scripters who work with JMP Scripting Language (JSL) will learn best practices to enable them to modernize their own development environment.

    Predictum's recently streamlined development workflow leverages new platforms, technologies, and automated processes for coding and testing with JMP Scripting Language (JSL) and other programming languages. Predictum’s software engineers are experiencing higher gains in development and quality assurance in the face of increasingly stringent requirements for quality, compliance, and security.

    The presenters will demonstrate the key components of the updated development environment and how they work together to boost the team’s daily work:
    • Visual Studio Code with JSL extension - a single code editor to edit and run JSL commands and scripts in addition to other programming languages
    • GitLab - a management hub for code repositories, project management, and automation for testing and deployment
    • Continuous integration/continuous delivery (CI/CD) pipeline – a workflow for managing hundreds of automated tests using Hamcrest that are conducted on multiple operating systems, software versions, and other interoperability requirements
    • Predictum System Framework (PSF) 2.0: our library of functions used by all client projects, including custom platforms, GitLab and CI/CD pipeline integration, helper functions, and JSL workarounds

    Who Should Attend:

    Developers and testers in engineering and science who work with JSL commands and scripts for analytical applications
  • Facilitating CMC Development and Regulatory Filings with Phase-Appropriate QbD Recorded: Jun 2 2020 54 mins
    Tiffany Rau, PhD, Rau Consulting LLC, Phil Ramsey, PhD, Predictum Inc., and Wayne Levin, Predictum Inc.
    Pharmaceutical and biotechnology companies are under increasing pressure to reduce timelines and costs to speed up the delivery of safe and high-quality products to patients. Even though timelines may change, the activities within the CMC regulatory pathway must be fulfilled and it is essential to look at the CMC program holistically and in early development.

    Phase-Appropriate Quality by Design (QbD) is a systems approach to drug development and manufacturing that mitigates risk and facilitates regulatory compliance and successful outcomes. In this session, we will give an overview of our strategy for applying phase-appropriate QbD from early process development to commercialization to increase the rates of success. Learn the role of predictive modeling in enhancing QbD and new methods that it employs. Practical topics will include:

    • Systems thinking in QbD
    • Introduction to building predictive models from Design of Experiments (DOE) and other data sources, even when only small data sets are available
    • How to tailor data analysis to be performed during process development to uncover the maximum insights to address existing challenges and mitigate risk throughout the early to late stages.

    Who Should Attend:

    Scientists, engineers, and project leaders who work in drug development, process development, technology transfer, or CMC projects in the pharmaceutical and biotechnology industries
Elevating the productivity of engineers and scientists
Our subject matter experts and software engineers present a range of topics on how engineers and scientists can leverage advanced analytics and statistical training in their daily work for continuous improvement and greater productivity.

Embed in website or blog

Successfully added emails: 0
Remove all
  • Title: Converging DOEs and Machine Learning with Self-Validating Ensemble Modeling
  • Live at: Oct 21 2020 3:00 pm
  • Presented by: Christopher Gotwalt, PhD, SAS Institute | Philip Ramsey, PhD, Predictum Inc. | Wayne Levin, Predictum Inc.
  • From:
Your email has been sent.
or close