Tuesday, May 26, 2026

場域應用與服務設計 Syllabus 2026 Fall

 張耀仁教授

1. 這些主題都以 AI 輔助、不需自行撰寫底層程式

2. 為了教學與示範、便於助教支援、確保功能與介面一致、評分與範例可重現,本課程限定使用業界主流的 Claude AI,有特殊原因必須使用其他AI者需在選課前與老師商量。

9/15 Introduction


AI Tool Decision 


    py & bash execution tool use & container

    9/22, 9/29  Prompts

    Prompts for scientific accuracy

    Science optional

    Prompt Engineering Guide

    合成物件


    10/6- Visualization

    10/13 Reasoning for Complex Problems

    Dog Retrieving Ball

    Reasoning with AI for Complex Constrained Problems: Dinner Scheduling 


    11/3 Circuit Optimization

    11/10 - 期中考暫停上課一次


    11/17, 11/24  RF IC Design (LNA), Part I

    極紫外光(EUV)光源, IEEE Spectrum: The Tiny Star Explosions Powering Moore’s Law

    Case Study: Apple C1 Modem LNA 


     12/1/2026 RF IC Design (LNA), Part II

       12/8/2026 RF IC Design (LNA), Part III

      12/15/2026 Analog IC Design (2-stage amp, AB, Diff Pair)

      12/22/2026 Analog IC P&R (of op741)
      12/29/2026 RF IC Design (RF PA Driver), Part I
      1/5/2027 RF IC Design (RF PA Driver), Part II


      End of Class


      backup

      12/1 RL

      RL


      12/8 RL




      12/15, 12/22  World Model for Artificial General Intelligence (AGI)


      12/29, 1/5 Machine Learning for Asset Management

      Wednesday, February 18, 2026

      Monday, February 16, 2026

      Tuesday, January 27, 2026

      學生回饋意見

        (稍微改寫去可辨視化)


      Monday, January 26, 2026

      AI 戰爭模擬

      使用對局理論(game theory) 模擬台海衝突

      3D 強化版

      台海衝突賽局理論分析模擬器 (連結)
      • 多方參與者:中國、台灣、美國、日本
      • 情境模擬:封鎖、入侵、灰色地帶、導彈打擊
      • 策略互動與升級風險分析
      台灣AI防禦戰略模擬 (連結)
      • 敵方導彈攻擊與攔截系統
      • 升級機制:無人機部署→雷達啟動→導彈發射
      俄羅斯無人機攻擊 vs 烏克蘭防空模擬 (連結)
      • 3D整合空戰防禦模擬系統
      • 攻擊與防禦系統的動態互動

      Tuesday, December 16, 2025

      HW#13 Reinforcement Learning (RL) 3

        自行決定是否做作業,做的話任選一題即可


      1. 市區交通模擬,如何控制燈號以增進運輸量 (RL)

       (credit: 與專題生共同創作)






       2. Use RL to train Submarine to avoid unmanned torpedo from attaching and attacking


      hi accomp share (artifact)


      3. Use RL to optimize a Manufacturing Process overcoming a failure,  artifact (share) (inspired by Edward Chang)






      4. Use RL to train inverted pendulum



      5. Train the robot in the following scenario to cross the road.

      scenario setting artifact









      6. Use RL to train submarine maneuvers







      7. Use TL to train the AI manager of  Supermarket (share)



      8. Use RL to train F1 racing


      9. Use RL to train TESLA FSD.