2025年5月28日 星期三

HW#14 Fractals

 1. Visualize fractals  

Make 4 types of fractals. Two of them are natural 3d objects such as clouds, lungs, blood vessels, ocean waves, and forests.

















share (Ocean fractal)



share (Build realistic trees)







share (Swiss Cheese)




share (recursive, Swiss Cheese)



share (Fractal Antenna)




share (打地鼠,Fractal version)




更多實例 fractals  





2025年5月26日 星期一

Cat coat color genetics

 







share 

News 

Calico and tabby 三花與虎斑可能產生的後代顏色





Tabby and Tabby 虎斑與虎斑可能的後代






Calico 三花可能的親代











Google Gemini 3 Pro App (calling Banana Nano)

2025年4月1日 星期二

AI 論文寫作與研究創新

P1 (從關鍵句出發)

According to the video clip "Laser weapons protect aircraft from surface- and air-launched threats" (Video Credit: Lockheed Martin), write a 3000-word report that surveys the latest technology about laser weapons on drone and aircraft defense.

Method 1: Give AI prompts and directly generate. Citations needed. Compile references in the end.

Method 2: Generate an outline first. Then generate one section at a time according to the outline. Citations needed. Compile references in the end.

Example


Prepare reports in English. Using AI-assisted translation, prepare reports in 繁體中文(台灣學術用字).

Illustration in svg

Laser weapon illustration

P2. (從關鍵字出發)

Write a report about Buck Converter.

Buck Converter diagram

P. 3 (如何將實驗數據撰寫成完整報告)

AI導航系統

因為 Claude 看得懂原始數據與實驗照片,它會根據這些資料寫成完整論文。

原始數據(課堂中提供): 期中報告初稿

Experimental data screenshot

P. 4 (如何將實驗數據撰寫成完整報告)

口袋營養師 (原始數據)

Pocket Nutritionist app

app

生成報告


P. 5 (如何運用AI 找到研究題目)

相關AI 技術與2 nm製程演進: https://claude.site/artifacts/334bcef9-522c-48a8-8bce-186a98b09e0c

AI缺陷檢測從5奈米提升至2奈米的綜合分析: https://claude.ai/share/93d2e3d9-f1a0-44e3-b735-b293ee28ac5d

演算法: https://claude.site/artifacts/681ffd88-1b5f-4a8a-b63a-054e23b3b91f

學術研究: Google Scholar Search

Wafer 檢測 benchmark (有81萬張晶圓瑕疵): https://www.kaggle.com/code/ashishpatel26/wm-811k-wafermap

Wafer map data

P. 6 (如何從現有研究找到創新的題目)

半導體機台預防性維護的AI 運用

2025年3月27日 星期四

健康照護科技專題(二) Syllabus 2025 Fall

(切換完整版課綱)

開場


Unit 1: AI Computer Vision

CNN (Convolutional Neural Networks) Handwashing

YOLO  (You Only Look Once) YOLOv7 list

ViT (Vision Transformers) wafer defects heat map comparison

VLM (Vision Language Models) nutrition analysis

Tesla AI Vision

HW#1 AI in Computer Vision


Unit 2: 盲人環境輔助理解,空間導航

空間資訊與識別輔助 


真實世界 3d 模型製作

HW#2 Understanding environments


Unit 3: 3d障礙偵測演算法

障礙偵測(Recast 原理)

動態障礙偵測

Simulating A Navigation Assistant with sonar 

HW#3 Obstacle detection



Unit 4: 避障演算法

Voronoi an introduction, Voronoi for Place Names 

Voronoi 2D navigation (show Voronoi) (Rural Road 2d)

Voronoi-based Safe Routing Planning (Country Alley  2d)

Voronoi waypoints for navigation (share) (Campus Alley 3d) vs. non Voronoi 



  • Unit 5: 環境安全檢測與評估視覺化 using Claude

    Hazard detection (環境危害偵測)


    Home Hazard chain identification and animation (居家危害鏈偵測與危害視覺化)




    Unit 6: AI實踐產品設計自動化

    A* for AI 




    Unit 8 Space-Time Evolution

    RL Follow up

    Geological evolution


    Unit 9 Advanced Prompts

    RL Follow up


    規模 9.0 程式設計的地震 


    Prompt Engineering Guide

    Japan in Geological evolution



    Prompts for scientific accuracy