AI在IC設計與PCB產業的應用

Overview of Circuit Design

PCB

AI 在PCB設計的應用 KiCad, Zener by Diode Computers

• PCB Pipeline Process (share)
•  PCB 生成

鑽孔路徑演算法

電路板鑽孔程序模擬

TSP 優化推進 PCB 製造業發展研究報告 (英文版含文獻 )

RL

• PCB Layout Optimization  using RL
• Advanced with stopping criteria, optimized 

Syllabus 科技英文與科普傳播 2025 秋天

上課方式: 使用科技英文學習掌握AI運用技巧，從實做中學習AI領域的技術應用能力與未來科學工程素養。

講授，工作坊，作業

學生請自行攜帶手機，平板或筆電。

本課程特色

---

9/10/2025 - Week 1: Introduction

百工如何使用ＡＩ (SVG)

受影響職業

最好的程式語言 (Python? JavaScript?)

提示使用英文的重要性

為什麼我的AI跟你不一樣

上學期本課程成績分布

AI 在半導體產業的應用

ＡＩ 在電子產業的應用

AI 作為一種實驗科學

Claude 4.5

Gemini 3.0

課程主題一覽表 svg

9/17/2025 - Week 2: Boosting human brains with AI

增強ＡＩ的能力

9/24/2025 - Week 3: Reasoning with AI for Complex Constrained Problems

推理模式 special topic: Smart Dog Ball Retrieval

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

AI半導體廠製程優化

10/1/2025 - Week 4

Timeline for dinner scheduling

Generate programs for dinner schedule (AI半導體廠製程優化)

River Puzzles (半導體晶圓廠情境 Part 1)

10/8/2025 - Week 5

AI Helper

Follow up

River Puzzles Part 2

10/15/2025 - Week 6

Follow up

Make AI smarter

10/22/2025 - Week 7

Catch up

Make AI smarter (Dinner Operation etc) Part 2

10/29/2025 - Week 8

Backtrack

A* macro thinking for electronic engineering problems

Circuit Optimization

11/5 - 期中考不上課

11/12/2025 - Week 9: Visualization

Update of new Claude Sonnet 4.5

AI 互動的基礎：如何與 AI 有效溝通 (Prompt 基礎篇) Pt 1

工程動畫 Pt 1，精選

11/19/2025 - Week 10

工程動畫 Pt 2

AI 互動的基礎：如何與 AI 有效溝通 (Prompt 基礎篇) Pt 2

11/26/2025 Scientific Animation

Blue LED

3d 物件與互動 (水與冰)

Cat coat colors: 貓的花色遺傳模擬

Simulating Laser

AI for Scientific Discovery

12/3/2025 - Week 12 High Complexity Animation

Follow up #11

隨機程序模擬

Enhance visualization (Mul. Iter. Merg.)

12/10/2025 - Week 13: RL

Follow up High Complexity Animation

RL

12/17/2025 - Week 14: Reinforcement Learning

Follow up RL 2

Geological evolution of Taiwan

聖誕節放假

12/31/2025 - Special Topics

Follow up RL 3

English origin

---

Backup

規模 9.0 程式設計的地震 

3d models from photos

Fractals: 美麗碎形世界

演算法視覺化

Build an AI APP

ancient language

---

Further Materials

• Taiwan Determined to Remain ‘Indispensable’ Source of Best Chips (Bloomberg)
• BBC Nature
• Japan top inventions | NHK
• Science view | NHK
• Science that can save your life | NHK

Implementation of systems based on paper/report

 

ATM Simulator (paper, download)

shower training (paper, download)

revision batch 1

revision batch 2

revision batch 3

Agility Training (artifact, 2d version), paper

Agility Training (share, 3d version), paper

hand washing (paper, download)

Community-based Purchasing skills, paper

照護app (from paper to app)

VLM-based Navigation (From paper to app) 

share

EX#15 Capstone test

 1. solve the strategic thinking problem

2. Visualize one of the scientific problems.

3. Visualize one of the mathematical programming problems

4.  Choose one of the following problems.

 You must implement the system from scratch based on the paper.

shower training (paper)

Agility Training (artifact, 2d version), paper

Agility Training (share, 3d version), paper

hand washing (paper)

EX#14 Fractals in real worlds

4. identify hazards in a fractal 3d assessment display, first person perspective, according to a real world photo. 

Choose any photo to proceed with.

依據照片重建三維場景，越自然越好（例如樹木，雲層等自然物件），需考慮視角與觀測位置轉換以便可以瀏覽各處細節，至少提供三個觀察點

至少選取一張照片(可使用自選)

artifact (non Fractal version)

artifact (fractal version)

share (artifact)

share

artifact (first person perspective)

artifact (non Fractal version)

artifact (fractal version)

Photo Galleries

Strategic thinking

  Devise a strategy for the dog in the picture to retrieve its ball that fell into the pond without getting its body wet, with no humans nearby to help."

This is a problem-solving or creative thinking exercise asking someone to come up with a plan for how a dog could get its ball back from water without getting wet and without human assistance.

Animate your strategy in svg or in 3d.

Solution 1

3D Use of float bridge , 

3D use of float bridge (thought out by Claude itself) Veo 2 (video w/ base image)

float bridge Imagen 4, another, Veo 2 (video)

Solution 2 

float + paddling inspired by student

Solution 3

3D, base 2D float push, wave making, another 2D

solution 4

Noodle Nudge Veo2 imagen 4

many clever strategies by Gemini 2.5 Pro

original video on social media

Algorithms

ＱuickSort  是常用的數字排序演算法，我們使用ＡＩ來視覺化它的排序過程，可以清楚看到數字如何逐漸由小排到大。 

QuickSort 演算過程視覺化。 

Illustrate in SVG the code.

汽車導航常常需要計算兩地之間最短路徑。我們用ＡＩ視覺化一個有名的最短路徑演算法（Dijkstra's Algorithm），你可輸入網路節點數，或是你希望的視覺化方式。

Shortest Path Algorithm

Traveling Salesman Problem 簡稱TSP

 (一個推銷員要拜訪所有客戶城市，每個城市只能拜訪一次，最後要回到出發城市，請為他/她計算最短的拜訪路徑)

TSP在工業界有重要應用，包括物流（UPS/Amazon配送路線優化）、製造業（電路板鑽孔、機器人組裝路徑）、電信（網路路由、線路安裝）和能源（電網維護、管線檢查）。凡是需要造訪多個地點同時最小化成本、時間或距離的場合都適用。現代變體能處理容量限制、時間窗口等實際約束。企業使用OR-Tools、Gurobi等專業軟體解決這些問題，透過優化倉儲揀貨、切割模式、3D列印路徑和車隊管理等作業，往往能節省數百萬成本。

(樸素) Visualize TSP (Traveling Salesman Problem) by A* search 使其可以改變網路節點個數

(美學) 視覺化 A* for Traveling Salesman Problem 使其可以改變網路節點個數

給定一個電路板，進行鑽孔程序模擬的優化 (建議 AI 一個演算法，例如A*, Greedy Method...)

A* Drilling

電路板鑽孔程序模擬

AI 在 PCB 產業的應用

A* 演算法

以下迷宮問題，比較 Ａ* search 與 Dijkstra 求解過程

A* search vs. Dijkstra for a maze

 Tower of Hanoi 

Amplifier Gain and Frequency Response Using AI

standard strategy

solve for gain

do not ignore bias current

calculate miller effect

calculate poles for lower cut off

calculate poles for higher cut off

plot bode plot gain vs. Hz

plot bode plot phase vs. Hz

lab share slides

Make Bode plot:

• Use of Gemini 3.0 Pro slides (Example 1, CE)
• Use of Claude Sonnet 4.6 slides (Example 1, CE)

step-by-step prompt share slides

single prompt share slides

• Electronics, Example 7
• Electronics, Example 6
• Electronics, Example 5
• Electronics, Example 3
• Electronics, Example 2
• Electronics, Example 1