WKU Data Analytics Awareness Webinar Series with Altair

Presenter: Harrison Murphy - Director of Data Analytics Solutions, Specialists, Analytics & IoT

Abstract: Machine Learning, Artificial Intelligence, and Data Science have never been more accessible or as widely proliferated in day-to-day life as they currently are and will continue to be for the near future. I would also argue that it's never been as widely misunderstood as it is currently. From Generative AI and Large Language Models like ChatGPT to AI-generated art and self-driving cars, it's easy to think of AI and ML as this unobtainable, all-encompassing, futuristic wonder technology when the reality can be simpler, more practical, and more tangible than previously considered.

We want to pull back the curtain and demystify what a typical data science process can look like from a non-technical user's perspective to bridge the gap between theory and practical application.

In this talk we're addressing:

• What is the data science process and how has this been traditionally accomplished?
• How can I apply my data and industry knowledge to the process?
• What are the current trends in the industry?
• What's available to me today and where do I get started?

Presenter: Scott Genzer - Senior Data Scientist

Abstract: With AI being the buzzword across every company and every business executive’s desk in the USA and abroad, the proverbial “elephant in the room” remains the same: remarkably few AI projects ever make it to the factory floor. And even fewer produce real business value to the company’s bottom line. So how can we learn from the past and help companies, particularly in laggard verticals such as industrial manufacturing, beat the odds? The answer is not simple but in this talk, we attempt to answer it with the following guiding questions:

• What do typical industrial manufacturing AI use cases look like?
• How should companies choose use cases that will have the highest likelihood of success?
• Who are the key stakeholders for success and what are their roles?
• What does an end-to-end industrial manufacturing AI project look like, from beginning to end?

Presenter: Jaideep Bangal – Director of Simulation & Design

Abstract: As digital engineering advances, modeling, and simulation will converge with machine learning, AI, and high-performance computing (HPC) in solving the world’s most complex problems. PhysicsAI is a new tool designed to predict physics outcomes quickly. This technology leverages historical simulation data to deliver fully animated physics predictions in a fraction of the time it takes traditional solvers to do the same. Unlike previous machine learning technologies, PhysicsAI uses cutting-edge geometric deep learning to operate directly on meshes and CAD models, which generates even faster results.

During this presentation, we discuss:

• How AI is used in computational engineering, with focus on manufacturing feasibility simulations and predictions using PhysicsAI.
• The challenges present in AI adoption, such as the difficulty of collecting meaningful data for training machine learning algorithms and capturing and understanding design intent.
• Specific AI tools and technologies that can be used in computational engineering, such as
  • Altair® romAI™ for generating reduced-order models (ROMs),
  • Altair® PhysicsAI™ for quick physics predictions, and
  • DesignAI for combining physics-based, simulation-driven design with machine learning-based AI-driven design.