AI-Driven Computational Design

• Understand formal grammars and procedural modeling

• Describe applications for design grammars

• Use geometric deformation methods for image/shape manipulation

Discussion Forum: Single Design vs. Design Space

Assignments: 

• Constructing a Design Space

• Expanded Parametric Design Exploration

• Understand the differences between linear, nonlinear, diffusion, and large language models (LLMs)

• Analyze use cases for data-driven models

• Describe the challenges facing designers and engineers when integrating generative AI models into their workflows

• Examine prompting techniques for refining LLM outputs

Discussion Forum: Large Language Models for Design

Assignment: Exploring Shoe Designs with an Autoencoder

• Understand how to predict and optimize performance metrics for design configurations

• Learn tools such as simulations, surrogate models, and LLMs for performance evaluation

• Explore trade-offs between precision and efficiency in design evaluation workflows

Assignments: 

• LLM-Based Design Evaluation Simulation

• Implementing a Surrogate Model to Estimate Design Performance

• Building a Physics-Informed Neural Network for a Damped Harmonic Oscillator

• Identify applicable reduced design spaces for inverse design

• Understand the steps of topology optimization

• Describe Bayesian optimization and identify potential applications

Assignments: 

• Bayesian Optimization for Black-Box Function Optimization

• Design Optimization

• Topology Optimization

• Understand the potential of generative AI to reshape creative design workflows

• Define the challenges of balancing automation with human creativity

• Describe how to incorporate these technologies into real-world applications

Assignment: 

• Using Generative AI Design Tools for Creative Design

• Explore how generative AI facilitates the translation of digital designs into actionable manufacturing instructions, bridging the gap between design and production

• Learn to use AI-driven methods, including compilers and LLMs, to optimize fabrication workflows and increase manufacturing efficiency

• Evaluate the potential of digital feedback loops and predictive models to improve product quality and sustainable manufacturing practices

Assignment: 

• Utilizing an LLM for Manufacturing Planning

Using simple text prompts and AI workflows, you can describe ideas and concepts in plain language, and generative AI models turn them into images, media, and other visual assets. This gives you the ability to explore more options, faster and at a higher quality than manual methods.

The program introduces AI surrogate models that can efficiently predict design performance and support simulation-driven design workflows. These approaches share characteristics with digital twin technologies, although the program focuses primarily on design performance prediction and optimization.

You will get full access to video lectures, assignments, and online forums where you can connect with your peers and instructors. You will also receive feedback on assignments to track your progress and knowledge throughout the program, and you can always reach out to the program support team with more questions.

This program is built for design, engineering, and manufacturing professionals as well as early-career professionals and advanced learners looking to grow their careers in the age of AI effectively. You will gain practical experience in industry software, including Fusion 360, OpenSCAD, and ChatGPT, along with the skills needed to open new job opportunities with clients and teams across a wide range of engineering, product development, and manufacturing-intensive industries.

Unlike other online courses on generative AI skills, this program also covers the equally important ethical aspects of AI in design, so any person can apply these methods responsibly throughout their professional life.