๐Ÿš€ Super AI Engineer Thailand 2026

AI in the Real World
Fast & Scalable Object Detection

Workshop designed for the next generation of Thai AI engineers. Learn how modern object detection systems are optimized, compressed, accelerated, and deployed under real industrial constraints.

Lecture by Pโ€™Kao โ€” Teerapong Panboonyuen, Ph.D.

๐ŸŽฏ What Students Will Learn

  • โšก Latency vs Accuracy Trade-offs
  • ๐Ÿง  Knowledge Distillation
  • โœ‚๏ธ Structured Pruning
  • ๐Ÿ”ข INT8 / FP16 Quantization
  • ๐Ÿ“น Multi-Camera Deployment
  • ๐Ÿš€ Real-Time AI Optimization
  • ๐Ÿ—๏ธ Industrial AI Engineering Mindset

๐ŸŒ Workshop Overview

Unlike typical tutorials focused only on benchmark accuracy, this workshop explores the hidden engineering trade-offs behind deploying scalable object detection systems in production. Students will experience how real AI products are engineered under computational, memory, and deployment constraints.

Performance

โšก Latency vs Accuracy

Understand how detection systems balance inference speed, throughput, and accuracy in real-time environments.

Optimization

โœ‚๏ธ Model Compression

Learn pruning, quantization, and lightweight architecture design for efficient deployment.

Deployment

๐Ÿ“น Scalable AI Systems

Explore production-scale pipelines, multi-camera inference, and GPU scheduling strategies.

๐Ÿงช Workshop Curriculum

Six hands-on labs covering optimization techniques, scalable deployment, and industrial computer vision systems.

โšก Lab 1 โ€” Baseline Profiling

Benchmark latency, FLOPs, FPS, and mAP across different YOLO variants.

โœ‚๏ธ Lab 2 โ€” Structured Pruning

Compress object detection models while preserving performance.

๐Ÿ”ข Lab 3 โ€” Quantization

Deploy INT8 and FP16 optimized detectors for faster inference.

๐Ÿง  Lab 4 โ€” Knowledge Distillation

Transfer knowledge from large teacher models to compact student networks.

๐Ÿ—๏ธ Lab 5 โ€” Architecture Design

Design scalable multi-scale detection heads and efficient backbones.

๐Ÿ“น Lab 6 โ€” Multi-Camera Deployment

Build scalable AI pipelines for production-scale video analytics systems.

๐Ÿง  Educational Philosophy

This workshop goes beyond academic toy examples. Students will experience real deployment constraints, engineering trade-offs, and industrial AI thinking.

โ€œA model that is accurate but unusable in production is not enough.โ€

The future of AI engineering is not only about building larger models, but building systems that are deployable, scalable, efficient, and practical in the real world.

๐Ÿ‘จโ€๐Ÿซ Lecturer

Teerapong Panboonyuen, Ph.D. (P'Kao)

Chulalongkorn University, Thailand

Research Focus: Efficient AI Systems โ€ข Computer Vision โ€ข Remote Sensing โ€ข Edge AI โ€ข Industrial Deep Learning

GitHub Contact

๐Ÿ“š Resources

Slides

๐ŸŽค Lecture Slides

Complete lecture slides for AI optimization, deployment strategies, and scalable object detection systems.

View Slides
Hands-on

๐Ÿ““ Colab Notebook

Interactive workshop notebook for profiling, pruning, quantization, and deployment experiments.

Open Colab
Repository

๐Ÿš€ GitHub Repository

Official workshop repository containing lecture materials, notebooks, and educational resources.

Visit GitHub