Professor of Mechanical Engineering
AI for Design and Optimization
What You'll Learn
- Learn the fundamentals of artificial intelligence (AI) relevant to engineering design and optimization processes
- Enhance engineering design creativity and optimize strategies by applying AI techniques
- Learn to discern appropriate applications of AI to ensure effective integration into workflows
- Learn to interpret outputs generated by AI models accurately
3 Modules
9 Hours
3 hrs per module (approx.)
Rating
About AI for Design and Optimization
Artificial intelligence and machine learning are revolutionizing design processes, optimizing strategies, and fostering innovation across industries. "AI for Design and Optimization” offers you the knowledge to harness the power of AI to enhance your own design and optimization capabilities. Mastering key skills such as discerning appropriate AI applications, interpreting model outputs, staying abreast of AI advancements, and effectively communicating the role of AI in projects is essential to effectively leverage these technologies in your practices. You will delve into the fundamentals of AI and their practical application in design and optimization, exploring advanced techniques like generative design, evolutionary algorithms, and topology optimization. This unique curriculum provides a comprehensive introduction to utilizing AI to enhance design creativity and streamline processes.
Skills You'll Gain
- Computational Design
- Generative AI Agents
- Machine Learning
- Multidisciplinary Design Optimization
What You'll Earn
- Certificate of Completion:
- Certificates of completion acknowledge knowledge acquired upon completion of a non-credit course or program.
Welcome Message
Welcome to AI for Design and Optimization, a course introducing how artificial intelligence and machine learning enhance design, optimization, and innovation. You will explore AI applications such as generative design and topology optimization while learning how to interpret model outputs and communicate AI-driven insights. The course blends practical exercises with industry-relevant design challenges.
This abbreviated syllabus description was created with the help of AI tools and reviewed by staff. The full syllabus is available to those who enroll in the course.
Course Schedule
Module 1: Introduction to Key Concepts and Fundamentals of Artificial Intelligence (AI) and Machine Learning (ML)
- Video: Introduction to Key Concepts
- Reading: Course Syllabus
- Reading: Help Us Learn About You!
- Reading: Introduction to Jupyter Labs on Coursera
- Video: Machine Learning Algorithms
- Video: Deep Learning and Neural Network
- Reading: K-Nearest Neighbors Implementation
- Ungraded Lab: K-Nearest Neighbor - Programming Exercise
- Reading: DNN Implementation
- Ungraded Lab: Neural Networks - Programming Exercise
- Video: Introduction of AI/ML in Design and Optimization
- Reading: Overfitting and Underfitting of ML
- Graded: Module 1 Assignment
Module 2: Generative Design Techniques
- Video: Generative Design Principles
- Video: Introduction to Algorithms and Techniques
- Video: Generative Adversarial Networks
- Reading: GAN in Pytorch Implementation
- Ungraded Lab: Generative Adversarial Networks- Programming Exercise
Module 3: AI-Driven Optimization Algorithms
- Video: Overview of Optimization Problems
- Video: Introduction to Optimization Algorithms
- Reading: Case Studies: Thermal Insulation Optimization
- Reading: Thermal Insulation Optimization
- Ungraded Lab: Thermal Insulation Optimization - Programming Exercise
- Video: Introduction of Topology Optimization
- Video: ML for Topology Optimization
- Video: Case Studies
- Reading: Case Studies: Battery Fast-Charging Optimization
- Reading: Battery Fast-Charging Optimization Implementation
- Ungraded Lab: Battery Charging Optimization - Programming Exercise
- Reading: End of Course Survey
- Reading: References
- Graded: Module 3 Assignment
Grading Policy
Each module includes a graded assignment, which accounts for 100% of your final grade. A minimum score of 80% on each assignment is required to earn a certificate.
Course content developed by U-M faculty and managed by the university. Faculty titles and affiliations are updated periodically.
Intermediate Level
Learners with general college-level education, industry-relevant experience, and professionals interested in the field are welcome.
