星期三, 4月 30, 2025

EX#9 3d model


使用Claude Sonnet 3.7 將場景照片轉為3D 模型,使用第一人稱視角,須具備 React 互動操作特性

增加 碰撞偵測,碰撞阻止

增加 物件互動(玩具靠近會招手...)



圖庫






 



星期二, 4月 22, 2025

EX#8 Visual Learning

1. 製作印歐語系"母親"("父親","眼睛","雪")的演進

(參考 "百"的演進 


2.  電子系的科技英文  remix ex:半導體元件的科技英文

 科學英文 remix ex:量子力學的科技英文

以上二者任選一項



3. 參考郵票設計,選擇下列一項

製作薛丁格方程式 100 周年紀念郵票

哥白尼 550 周年紀念郵票

愛因斯坦 70 周年紀念郵票

或你喜歡人物的紀念郵票(藝術家,演員,歌手,...),任選一項



4. 3D 物理模擬

參考以下水與冰的相變,製作一個3D物理模擬













share (quantum level)












星期五, 4月 11, 2025

Semiconductor Component Transfer








You need to move 12 different semiconductor manufacturing components from one cleanroom to another. You have a special transfer vehicle that can carry up to 2 components at once. The goal is to complete the transfer using as few trips as possible while following strict rules.

The Extreme Challenge Rules: 1. Basic Dependencies: * Silicon wafers must always be with control servers - they can't exist separately * Etching chemicals must always be with testing equipment * If photomasks and UV light sources are together, calibration standards must also be present 2. Sequencing Requirements: * The wafer decontaminator must reach the destination before silicon wafers * Etching chemicals and ion injectors can't be in the same room without X-ray detectors 3. Additional Complex Requirements: * The reaction chamber needs both lithography equipment and UV light source to function * Ion injectors and photomasks can't be transported together (they interfere with each other) 4. Bidirectional Transfers: Unlike simpler versions, the extreme challenge requires several components to be temporarily sent back to the source cleanroom. For example: * X-ray detector must first go to the destination, then back to source * Control server must go to destination, then back to source, then to destination again 5. Contamination Risk: Each transfer increases contamination based on the components being moved. Some components have higher contamination risk than others. If total contamination reaches 100%, the transfer fails.

Semiconductor Component Transfer Solution

Let's create a step-by-step plan that minimizes trips while respecting all dependencies, sequencing requirements, and bidirectional transfer requirements.

Optimal Transfer Solution (10 trips)

Trip 1: Move Wafer Decontaminator and Lithography Equipment to destination

Note: Wafer decontaminator must be at destination before silicon wafers

Trip 2: Move X-ray Detector and UV Light Source to destination

Note: X-ray detector begins its required path (source→destination→source)

Trip 3: Move X-ray Detector and UV Light Source back to source

Note: X-ray detector continues its required path

omitted

Trip 8: Move UV Light Source and Photomasks to destination
Note: Photomasks and UV light source are now together with calibration standards

Trip 9: Move Etching Chemicals and Testing Equipment to destination

Note: These components must travel together

Trip 10: Move Ion Injectors and Reaction Chamber to destination

Note: X-ray detector is already at destination, allowing ion injectors and etching chemicals to be in the same room

Verification of Rules

  1. Basic Dependencies:

    • Silicon wafers and control servers are always together ✓
    • Etching chemicals and testing equipment are always together ✓
    • Photomasks, UV light sources, and calibration standards end up together ✓
  2. Sequencing Requirements:

    • Wafer decontaminator reaches destination before silicon wafers ✓
    • Etching chemicals and ion injectors are never in the same room without X-ray detectors ✓
  3. Complex Requirements:

    • Reaction chamber, lithography equipment, and UV light source all end up at destination ✓
    • Ion injectors and photomasks are never transported together ✓
  4. Bidirectional Transfers:

    • X-ray detector: source → destination → source → destination ✓
    • Control server: source → destination → source → destination ✓

All components have been successfully transferred to the destination with the minimum possible 10 trips while adhering to all constraints.

星期二, 4月 08, 2025

EX#7 科技動畫

  如何繳交作業 How to turn in your homework exercise.  


課堂練習的工具 

使用 Claude Sonnet 3.7

使用 ChatGPT 4o, o1

使用 Gemini 2.0 Flash

使用 Grok 3


課堂練習繳交期限 

Deadline: 

1. end of session 

2. This Saturday at 4/22 23:59


課堂練習繳交方式 

Send all the links to TA victorhuang111013@gmail.com and me chang212@gmail.com by email with subject EX#7  [your ID, your name]



1. 語文起源學的玩樂場,製作動畫遊戲,最後加上通關測驗至少答對7/10


2. Select 2 words in the quiz answers above, make etymology illustrations for them using SVG or REACT with icons.







3. uni- vs. mono

製作遊戲,可有效學習 uni- vs. mono 字根的差異






4. 據業界推估,台積電和三星等領先企業已成功應用遷移學習,將CVD設備的模型遷移至PVD設備,將檢測效率提高50%以上,同時減少80%的新模型訓練時間。

(半導體潔淨室轉移問題) 渡河大作戰最佳排程 高速版,AI 推理約需3-10分鐘,用AI生成Python程式,可加快執行速度到千分之一秒以下 。可以參考 Use Code Gen to solve River Puzzle 2 ,結果必須視覺化,動畫尤佳









學生優秀作品

Answer Keys to EX#6

 參考觀摩

光合作用



https://claude.ai/share/89ae2ef1-5676-4663-bab5-751b9ce9ab62




生物呼吸中的量子效應互動模擬




黑洞


非牛頓流體


水的量子微觀
https://claude.ai/share/9e2b67d5-c894-4ac2-ba93-e44b93b7282e

候鳥雌性導航的量子機制


Schrödinger Equation Visualization



星期三, 4月 02, 2025

Answer Keys to EX#5


LRASM: Long Range Anti-Ship Missile launched from F/A-18

LRASM: launched from warships

SM-3 Block IIA



River 1 渡河問題




 it takes 15 steps. (thanks to the python code generated by Claude)




another 15-step solution



yet another 15-step

one more 15-step

last 15-step


打開Sonnet 3.7推理模式
我目前還沒有辦法完全正確渡河
最好的一次用了2:57,錯在第12步,不過是個小失誤,不花腦筋很容易改

至於跑到耗盡token那次4:47,居然沒有給出答案


可以這麼說,這題渡河用 python 寫 A*
可以找到最佳解 15 步

我目前使用所有 no code 方式, 無論 ChatGPT, grok, Claude 各種推理模式,沒有一次能得到完美無瑕的解

Puzzle 3, 17 steps 



Sonnet 可能需要付費,有的同學是免費,但也有被要求付費

Remix 可以在 haiku做,效果可能會不一樣
但總比直接做好很多