深度研究: AI 正在改變半導體製造業
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,
Engine (credit: 碩專作品)
CVT 排檔 (credit: 大學部作品)
Jet Engine (credit: 大學部作品)
Visualize Bike gear change
Animate PVD, PECVD (Plasma-Enhanced Chemical Vapor Deposition)
(credit: 碩專作品)
每個對話( chat) 都有容許的記憶長度(context window),這跟人類是不一樣的,
規模的迷思 : AI 的規模與問題解決策略
當AI面對包含多個限制條件的複雜問題時,確實存在難度。
在注意力機制(Attention mechanism)中,模型需要同時關注多個條件,並且每個注意力分配都是基於概率的。當條件數量增加時,要同時滿足所有條件的概率會顯著降低,這就像是連續投擲硬幣並期望全部正面朝上一樣——條件越多,全部滿足的概率越低。
這種情況下,模型可能會:
如果您有一個包含多個複雜條件的問題需要解決,我建議將問題分解成較小的部分,逐步處理每個條件,這樣會更容易得到準確的解答。
1. 科學現象3d模擬(雷射,超導體,超流體,中子星碰撞...),選取以下一個題目,加上自選一個主題
a. 科學模擬 3d 化(使用 three.js 模擬 3d )
Black hole-star binary system simulation
黑洞與恆星雙星系統
b. 使用 three.js 模擬 3d
2. 雷射(2d 模擬 energy pumping)
雷射(3d 模擬) 使用3d量子場
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.
開課日期:2025年9月9日 (每周二 晚間 6:55 開始三節課)
課程目標:本課程旨在探討人工智慧(AI)的理論基礎、實際應用及對社會的影響。學生將通過互動式講座和實作練習,深入了解AI演算法、可視化技術、職場應用及社會創新項目。課程結束後,學生將能夠在專業、學術及日常情境中有效運用AI工具。
Topic: Course Introduction
Topic: AI Development Trends
Topic: Effective Prompt Engineering
Topic: Retrieval Augmented Generation (RAG) – Part 2: Applications
Topic: Chain of Thought (CoT) Reasoning
Topic: LLM-Assisted Academic Writing (Chain of Thought)
Topic: Advanced LLM Applications in Academic Work
Topic: Advantages and Limitations of LLMs
Midterm Break: No class (Pause for reflection or catch-up)
Topic: AI in the Workplace (Part 1)
Topic: AI in the Workplace (Part 2)
Topic: AI in the Workplace (Part 3)
Topic: AI in the Workplace (Part 4)
Topic: AI in Everyday Life
Topic: Open Session / Project Work
Topic: Project Presentations
Topic: Course Wrap-Up
什麼是「場域應用與服務設計」?AI 如何賦能服務設計? -> 介紹學期專案 9/9
最好的程式語言重新被定義 (Python? JavaScript?)
示範: AI 快速開發 無人機飛行模擬視覺化
AI 發展趨勢 9/16
AI 互動的基礎:如何與 AI 有效溝通 (Prompt)
9/23
9/30
讓 AI 擁有領域知識 -> RAG 理論與應用(Retrieval Augmented Generation)
練習: Understanding academic papers
10/7,10/14
AI 賦能專業工作 -> 以論文寫作為例 (研究、草稿、潤飾、數據分析) (思維鏈,Chain of thought)
練習: Enhance Writing by AI 1
AI 與 電子學 12/9, 12/16
學期專案發表與展示 (Final Project Presentations) 12/23