UAT 485 · 3(1-4-4) · Year/term 4/1

Edge AI Computing

การประมวลผลปัญญาประดิษฐ์ที่อุปกรณ์ปลายทาง

Progress
Notional hours: 135 h (online/self-study 60 · in class/lab 75)

Course description

edge-computing architectures, model-acceleration methods, model compression and quantization, real-time image and data processing, power management, sensor interfacing, and deployment of AI models on embedded platforms

Thai description

สถาปัตยกรรมอุปกรณ์ประมวลผลปลายทาง การเร่งการประมวลผลแบบจำลอง การลดขนาดและควอนไทซ์แบบจำลอง การประมวลผลภาพและข้อมูลแบบเวลาจริง การจัดการพลังงาน การเชื่อมต่อเซนเซอร์ และการติดตั้งแบบจำลองปัญญาประดิษฐ์บนแพลตฟอร์มฝังตัว

Description source: Curriculum draft (revised 28 Sep 2026)Previous site code: DRT 494

Course learning outcomes (CLO)

CLOOutcomePLO
CLO1Explain constraints of edge AIPLO4
CLO2Convert and optimise models for edge devicesPLO4
CLO3Measure and report performance on hardwarePLO4PLO5

Learning modules

1Edge AI for drones
Weeks 1–3 · 27 h
2 KU

Online (before class) · 12 h

Study the assigned knowledge units in advance, review media and take the module quiz

In class / field · 15 h

Lab or field practice from worksheets with a safety checklist

Learning evidence: Checked worksheets and quiz results

2Model conversion and ONNX
Weeks 4–6 · 27 h
2 KU

Online (before class) · 12 h

Study the assigned knowledge units in advance, review media and take the module quiz

In class / field · 15 h

Lab or field practice from worksheets with a safety checklist

Learning evidence: Checked worksheets and quiz results

3Quantisation
Weeks 7–9 · 27 h
2 KU

Online (before class) · 12 h

Study the assigned knowledge units in advance, review media and take the module quiz

In class / field · 15 h

Lab or field practice from worksheets with a safety checklist

Learning evidence: Checked worksheets and quiz results

4Edge hardware
Weeks 10–12 · 27 h
2 KU

Online (before class) · 12 h

Study the assigned knowledge units in advance, review media and take the module quiz

In class / field · 15 h

Lab or field practice from worksheets with a safety checklist

Learning evidence: Checked worksheets and quiz results

5Benchmark and deployment plan
Weeks 13–15 · 27 h
1 KU

Online (before class) · 12 h

Study the assigned knowledge units in advance, review media and take the module quiz

In class / field · 15 h

Lab or field practice from worksheets with a safety checklist

Learning evidence: Checked worksheets and quiz results

Assessment (draft)

Labs and worksheets35%
Module quizzes10%
Midterm examination20%
Mini-project or practical exam35%

Knowledge domain

Key references

  1. Warden, P., & Situnayake, D. (2020). TinyML: Machine learning with TensorFlow Lite on Arduino and ultra-low-power microcontrollers. O'Reilly Media.
  2. ONNX Runtime. Documentation. link