About Workshop
This 3-day hands-on workshop The Inverse Design Lab teaches researchers to optimize complex formulations using Bayesian Optimization and Gaussian Processes. Participants will learn to balance trade-offs, like strength vs. conductivity, by leveraging AI to model uncertainty and discover the Pareto Frontier. This hands-on workshop enables efficient experimental design, saving time and resources in material science, chemistry, and engineering.
Aim
AI-powered Bayesian Optimization and Gaussian Processes optimize formulations, balancing properties like strength vs. conductivity and refining designs with fewer experiments.
What Participants Will Learn
- Understand Gaussian Processes for small datasets.
- Master Multi-Objective Optimization using Bayesian Optimization.
- Optimize Experimental Design via the Pareto Frontier.
- Implement Active Learning to refine experiments.
- Apply AI to enhance experimental outcomes.
Structure
📅 Day 1 — The Mathematics of Uncertainty (Gaussian Processes)
- Introduction to Gaussian Processes (GPs) for modeling uncertainty in experimental data.
- Practical setup: Building a GP model in Python (BoTorch or GPyTorch) using experimental spreadsheet data (e.g., Composition % vs. Compressive Strength).
- Hands-on: Configure and run a GP model using personal experimental data.
- Deliverable: A plot visualizing the uncertainty and predictions from the Gaussian Process model.
📅 Day 2 — Multi-Objective Optimization & The Pareto Frontier
- Defining Acquisition Functions to guide AI in balancing exploration and exploitation.
- Visualizing the Pareto Frontier for trade-offs (e.g., Strength vs. Sorption). Learn how to optimize competing objectives simultaneously.
- Hands-on: Run a closed-loop simulation where AI suggests the next 5 experiments to maximize two conflicting variables.
- Deliverable: Visualize the Pareto Frontier and interpret the optimal balance between competing properties.
📅 Day 3 — Active Learning for Experimental Design
- Integrating human intuition with AI through Human-in-the-loop AI for refining experimental designs.
- Hands-on: Create a recommender system that takes previous experiment results and generates the next optimal synthesis recipe.
- Deliverable: A Python script that recommends the next experiment based on past results, optimizing for the desired outcomes.
Important Dates
Registration Ends
04:30 PM
Workshop Dates
2026-03-16
05:30 PM
05:30 PM
What You Will Gain
Outcomes
- Proficiency in Gaussian Processes for small datasets.
- Ability to apply Bayesian Optimization for multi-objective formulations.
- Skills in visualizing and optimizing the Pareto Frontier.
- Expertise in integrating AI and human intuition for experimental design.
- Capability to build AI-driven recommender systems for experiments.
- Improved efficiency and decision-making in experimental design using AI.
Who Should Attend
- Researchers and R&D professionals optimizing multi-component formulations with multi-objective trade-offs (often N < 50).
- PhD/postdoc/faculty/industry scientists in materials, chemical/polymer, civil/energy—incl. composites, coatings/adhesives, membranes, cementitious/grout.
- Ideal for teams moving beyond OFAT/limited DoE.
- Recommended: Excel/CSV + basic Python/Jupyter (no ML required).