NASA
Aqua Utopia｜海の底で記憶を紡ぐ
❣ Chile in a Photography ❣
art blog(derogatory)
Three Goblin Art
Kiana Khansmith
DEAR READER
wallacepolsom
Kaledo Art
RMH
almost home
occasionally subtle
"I'm Dorothy Gale from Kansas"
Monterey Bay Aquarium
let's talk about Bridgerton tea, my ask is open
ellievsbear
YOU ARE THE REASON
Product Placement
Peter Solarz
seen from Iraq
seen from Greece
seen from United States
seen from United States
seen from Netherlands
seen from United States
seen from United States
seen from Austria
seen from Türkiye
seen from Brazil
seen from Lithuania
seen from Switzerland
seen from Netherlands
seen from United States
seen from Malaysia
seen from United States
seen from United States
seen from Norway
seen from United States
seen from United States
@projectskeptic
MIT 6.034 Artificial Inteligence
Lecture notes
Lecture 2. Reasoning : Goal tree and problem solving
(대부분 integral program에 대한 것이라 간략히만)
- problem solving 이란 결국 풀기 쉬운 문제로 만드는 것 : problem reduction
- 메타 널리지 = 파워
- 인텔리전트하다고 생각되는 것들은 어떻게 구성되어 있는지 알고 나면 별로 안 인텔리전트해 보인다
Anya is live and ready to show you everything. Watch her strip, dance, and perform exclusive shows just for you. Interact in real-time and make your fantasies come true.
Free to watch • No registration required • HD streaming
MIT 6.034 Artificial Inteligence
Lecture notes
Lecture 1. Introduction and Scope
Definition:
Algorithms enabled by constraint exposed by representations that support models targeted at THINKING, PERCEPTION, ACTION.
생각, 인지, 행동을 목표로 하는 모델을 만들기 위한, 제약된 표상을 가능케 하는 알고리즘
MIT 6.034 Artificial Inteligence
Lecture notes
Machine Learning : notes
When some memorable concepts pop up during studying machine learning, I’ll keep them in this post comments. - 머신러닝에 대해 배우는 중. 기억할 꼭지들은 댓글로 노트를 남겨둔다.
[Support Vector Machine]
- Linear Regression의 한 종류.
- Margin이 가장 큰 line 혹은 하이퍼플레인을 찾는 것이 SVM의 목표.
- Margin이란 가장 가까운 data point와 line/hyperplane간의 거리.
- 왜 Maximize해야 하는가?
ㄴ dichotomy : 한 set을 2개의 subset으로 나눔
ㄴ shattering : classifier가 모든 subset을 다 나눌 수 있는가의 여부
ㄴ VC dimension : shattering 할 수 있는 최대 데이터 포인트의 수 (dimension M에 대해 M + 1)
ㄴ VC dimension이 줄어들수록 dataset의 error가 줄어든다. margin maximize는 이 VC dimension을 줄이는 과정.
Machine Learning : notes
When some memorable concepts pop up during studying machine learning, I’ll keep them in this post comments. - 머신러닝에 대해 배우는 중. 기억할 꼭지들은 댓글로 노트를 남겨둔다.
Laplacian Smoothing (라플라스 스무딩)
Overfitting 을 막기 위한 장치 중 하나. 발생할 확률들에 1을 더하여 확률이 0이 되는 것을 막는다. 기존의 발생 확률이 2/3인 것에 Laplacian smoothing을 적용하면 3/5가 된다.
https://en.wikipedia.org/wiki/Laplacian_smoothing
Anya is live and ready to show you everything. Watch her strip, dance, and perform exclusive shows just for you. Interact in real-time and make your fantasies come true.
Free to watch • No registration required • HD streaming
Machine Learning : notes
When some memorable concepts pop up during studying machine learning, I’ll keep them in this post comments. - 머신러닝에 대해 배우는 중. 기억할 꼭지들은 댓글로 노트를 남겨둔다.