1. Trang chủ
  2. » Công Nghệ Thông Tin

giáo trình môn chuyên ngành máy học

15 215 0

Đang tải... (xem toàn văn)

Tài liệu hạn chế xem trước, để xem đầy đủ mời bạn chọn Tải xuống

THÔNG TIN TÀI LIỆU

Thông tin cơ bản

Định dạng
Số trang 15
Dung lượng 548,5 KB

Các công cụ chuyển đổi và chỉnh sửa cho tài liệu này

Nội dung

Machine Learning Damon Waring 22 April 2003...  Machine Learning  “The study of computer algorithms that improve automatically through experience” –Tom Mitchell, Machine Learning 

Trang 1

Machine Learning

Damon Waring

22 April 2003

Trang 2

 Problem, Solution, Benefits

 Machine Learning Overview/Basics

 Face detection, recognition, and

demo

 How this applies to us

 Summary

Trang 3

Software frequently requires users

or developers to do simple,

repetitive tasks

Trang 4

 Machine Learning

 “The study of computer algorithms

that improve automatically through

experience” –Tom Mitchell, Machine

Learning

 Machine learning uses include:

 Security (Pattern recognition, face

recognition)

 Business (Stocks, user behaviors)

 Medical (Research)

 Ease of Use (Focus of this presentation)

Algorithms that execute based on experience

Algorithms that execute based on experience

Trang 5

 Makes human-computer interaction

easier

 Relatively simple to integrate

 Will distinguish your product from

others

 Increase customer satisfaction

 Will improve simple intelligent systems (ex: Microsoft Word’s grammar

checker)

Enhances the user experience

Enhances the user experience

Trang 6

High Level Operation:

Recognition Algorithms

 Training Set

 Iteratively analyze

inputs and refine

algorithm

 Store learned data

 Operation Mode Operation Mode

 New input

 Process input using learned data

 Produce a decision

Recognition algorithms are taught and react like humans

Recognition algorithms are taught and react like humans

“Learn from nature It has had 4 billion years

to develop its techniques” – My Dad

Trang 7

Case Study: Artificial

Neural Network

Neural Network

weight each input

has on final decision

if the decision is

true, 0 if it is false

make up an artificial

neural network

Group of weighted input values determine a binary output

Group of weighted input values determine a binary output

Trang 8

Face Detection

1 Image pyramid used to locate faces of different sizes

2 Image lighting compensation

3 Neural Network detects rotation of face candidate

4 Final face candidate de-rotated ready for detection

Trang 9

Face Detection (Con’t)

mouth, etc)

Trang 10

Face Recognition and

demo

 Demo: Hidden Markov Model Face

Recognition

respect to each other

“fingerprint” created by distances

between features

 Demo is from OpenCV – Intel’s open source computer vision library

Implementations vary widely and have different success rates

Implementations vary widely and have different success rates

Trang 11

Adobe Photoshop Album

 Software that organizes digital

pictures

 Tags are dragged to each photo to

categorize it

 Tagging 100’s of photos is tedious

 Face recognition could automatically tag photos or replace tags altogether

Machine learning can be used to make everyday apps easier

Machine learning can be used to make everyday apps easier

Trang 12

Current Uses of ML

accesses

Recognition to digitize newspapers

Deep Blue, but smarter because of

Neural Networks

Trang 13

Other Areas

Trang 14

 Machine learning is possible today

 Large amounts of research are available

 Quality open source code available in

some areas

 Will require time and creativity to

implement

 Why do it? Makes human-computer

interface simpler

Trang 15

http://sourceforge.net/projects/opencvlibrary/

Understanding,” “Artificial Intelligence,” “Neural Networks”

“Image Processing”

embedded HMM for face detection and recognition.” Nefian, A.V.; Hayes, M.H III; Image Processing, 2000 Proceedings 2000 International Conference on, Volume: 1, Pages 33-36

Analysis and Machine Intelligence, IEEE Transactions on, Volume 20 Issue 1, Jan

1998 Pages 23-38 (Paper posted at: http://www.ri.cmu.edu/projects/project_271.html )

http://www.ri.cmu.edu/projects/project_271.html

Ngày đăng: 03/07/2015, 15:49

TỪ KHÓA LIÊN QUAN

🧩 Sản phẩm bạn có thể quan tâm

w