醫院掛號系統

 

選擇日期

在月曆中選擇日期

生成結果

HW#3 Enhance Your AI (LLM)

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

課堂練習 

Deadline: This Saturday at 23:59

Send all the links to  me chang212@gmail.com by email with subject HW#3 Enhance AI [your id, your name].

任選兩題作答即可

練習: 任意製作一個動畫(旋轉的玩具風車，下潛的成熟抹香鯨，...) [繪圖可以快速檢視LLM是否理解人類的提示，檢視提示文字是否明確，清楚，具體]

練習: 將一張照片素描化 (森林與單車，繁忙的中原夜市，...，注意勿使用人身隱私照片) [素描可以用來快速檢視LLM 對影像的辨識與空間理解的能力，可以協助AI視覺應用的導入]

練習: 如何視覺化 /動畫碎形產生  Mandelbrot Set， Julia Set

Generating Fractals: Clear and Specific Prompt

 Visualize

Animate it (Fractal cloud)

Slow down

Mandelbrot Set

加上控制(縮放)

加上色彩

加上更多控制

加上選取觀看區域location 

選擇調色盤 color scheme

自動循環縮放 auto zooming

 Julia Set

 加上色彩

學生作品

學生作品+1

學生作品+1

Thomas Attractors 3D

樹木是碎形 (學生作品)

看不完的碎形

模擬自行車自動變速

給AI的提示: 

你是小巨人單車的研發工程師，你的任務是開發一套使用AI的自動變速系統，為了達成此任務，你需要能夠模擬自行車自動變速的系統。

模擬自行車自動變速

 

指定面板風格(視個人偏好)

模擬運動員騎乘 (Simulate an athlete.)

變速器作動視覺化 (Depict gear change as seen in an amateur bicycle.)

Focus on gear (mission: sales)

Manual shift 

學生作品remixed

學生作品remixed

自行輸入地形 (terrain)

HW#2: Visualization

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

課堂練習 

Deadline: This Saturday at 23:59

Send all the links to  me chang212@gmail.com by email with subject HW#2 Visualization [your id, your name].

練習: QuickSort 演算過程視覺化

練習: 模擬一個工程或科學系統，例如自行車自動變速系統，汽車自動排檔系統，...

HW#1 Whack-a-Mole

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

課堂練習 

Deadline: This Saturday at 23:59

Send all the links to  me chang212@gmail.com by email with subject HW#1 Whack-a-Mole [your name]

練習: 十分鐘做一支打地鼠遊戲 (一小時也無妨)

Whack-a-Mole

AI 現在進行式

回顧十年

(繁體中文版)

2012 

Alexnet, big bang of AI

Toronto University

ImageNet with 14 m images

Error 25 down to 15 %

G4 GTX nvidia

CNN

Alex krizhevsky

Llya sutskever

Geoffrey Hinton

2013 

Alex, Geoffrey found DNN

Sold to Google

Used to power social media feed recommendations

YouTube

Instagram

Duopoly by Google and FB

2015 

openai

Elon musk

Llya (left Google)

Andrej karpathy …

Found OpenAI

Image supervised

Language embedded structure (word learned by joint attention while language by self teaching)

2017 

the transformer paper by Google

Attention is all you need.

Large amount of data needed

Computationally expensive n squared complexity

GPU came in

Parallel nature

OpenAI turned for profit

2018 

ChatGPT 1

Predicting the next word in a sentence

2019 

ChatGPT 2

$1 B from Microsoft

2020 ChatGPT 3

2021

Copilot

$2 B from Microsoft

2022 (FTX fell, triggering mass layoffs of big techs)

ChatGPT 3.5 (nov 30)

$10 B from Microsoft

2023 ChatGPT 4

Outlook

Data center, cloud computing

X86 Intel based CPU

80% of streaming video

GPU comes in, on chip RAM

Parallel computing, graphics, video

Data center as one computer

Questions

1. LLM = AI?

2. Do exams well, enough?

3. Infants, animals, nonverbal

Cognitive test