GPMS TRANSPORTAL APPLIED AI COURSES

• This course dives deeper into the application of AI in the semiconductor manufacturing process, focusing on predictive maintenance, process optimization, defect detection, and yield improvement.
• Level: Intermediate
• Prerequisites: Knowledge of basic semiconductor principles and some exposure to machine learning.
• Assessments: Micro Assessment weekly, Full Assessment in the final week.

---

Week 1 - AI in Semiconductor Manufacturing Process

Learning Outcome

Understand the role of AI in automating and optimizing semiconductor fabrication.

1.1 Overview of semiconductor manufacturing.
1.2 Key challenges in the semiconductor fabrication process.
1.3 AI's role in automating tasks within semiconductor manufacturing.

Practical Component
Introduction to AI tools used in the semiconductor manufacturing process. Students will simulate the use of AI for process automation.

---

Week 2 - Predictive Maintenance with AI

Learning Outcome

Learn how AI can predict equipment failures and optimize maintenance schedules.

2.1 Predictive maintenance using machine learning models.
2.2 Anomaly detection in equipment performance data.
2.3 How AI improves machine uptime and reduces production delays.

Practical Component
Practical demonstration of how AI predicts machine failure based on historical data.

---

Week 3 - AI for Process Optimization in Semiconductor Fabrication

Learning Outcome

Students will learn how AI optimizes manufacturing processes such as etching, deposition, and photolithography.

3.1 AI models for process control and optimization.
3.2 Machine learning in real-time process adjustment.
3.3 Reducing variability in semiconductor production using AI.

Practical Componenet
Hands-on experience with AI tools optimizing process parameters in semiconductor fabrication.

---

Week 4 - AI for Defect Detection and Classification

Learning Outcome

Learn how AI tools detect defects in semiconductor wafers and classify defects to improve yield.

4.1 Using computer vision for defect detection.
4.2 Machine learning techniques for classifying defects.
4.3 The impact of defect detection on yield optimization.

Practical Componenet
Students will analyze wafer images using AI for defect detection.

---

Week 5 - AI-Driven Yield Prediction and Improvement

Learning Outcome

Students will learn how AI predicts yield rates and improves overall semiconductor production efficiency.

5.1 Machine learning models for yield prediction.
5.2 Improving yield using AI-based data analysis
5.3 Reducing scrap and increasing overall yield.

Practical Component
Apply AI to predict yield rates and improve semiconductor production quality.

---

Week 6 - Capstone Project and Assessment

Learning Outcome

Students will integrate AI tools into a semiconductor manufacturing workflow, optimizing key stages of production.

6.1 Full cycle of process optimization, defect detection, and yield prediction.
6.2 Peer assessment and final presentation.
6.3 Final feedback on project and overall learning.

Practical Component
Students will complete a full project integrating AI in semiconductor manufacturing processes, including defect detection, yield prediction, and process optimization.

---