The blue and green colors are actually the same
description
Transcript of The blue and green colors are actually the same
![Page 1: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/1.jpg)
The blue and green colors are actually the same
![Page 2: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/2.jpg)
http://blogs.discovermagazine.com/badastronomy/2009/06/24/the-blue-and-the-green/
![Page 3: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/3.jpg)
Machine Learning: Overview
Computer VisionJames Hays, Brown
09/19/11
Slides: Isabelle Guyon, Erik Sudderth, Mark Johnson,Derek Hoiem
Photo: CMU Machine Learning Department protests G20
![Page 4: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/4.jpg)
Machine learning: Overview
• Core of ML: Making predictions or decisions from Data.
• This overview will not go in to depth about the statistical underpinnings of learning methods. We’re looking at ML as a tool. Take CSCI 1950-F: Introduction to Machine Learning to learn more about ML.
![Page 5: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/5.jpg)
Impact of Machine Learning
• Machine Learning is arguably the greatest export from computing to other scientific fields.
![Page 6: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/6.jpg)
Machine Learning Applications
Slide: Isabelle Guyon
![Page 7: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/7.jpg)
Image Categorization
Training Labels
Training Images
Classifier Training
Training
Image Features
Trained Classifier
Slide: Derek Hoiem
![Page 8: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/8.jpg)
Image Categorization
Training Labels
Training Images
Classifier Training
Training
Image Features
Image Features
Testing
Test Image
Trained Classifier
Trained Classifier Outdoor
Prediction
Slide: Derek Hoiem
![Page 9: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/9.jpg)
Claim:
The decision to use machine learning is more important than the choice of a particular learning method.
If you hear somebody talking of a specific learning mechanism, be wary (e.g. YouTube comment "Oooh, we could plug this in to a Neural networkand blah blah blah“)
![Page 10: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/10.jpg)
Example: Boundary Detection
• Is this a boundary?
![Page 11: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/11.jpg)
Image features
Training Labels
Training Images
Classifier Training
Training
Image Features
Trained Classifier
Slide: Derek Hoiem
![Page 12: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/12.jpg)
General Principles of Representation• Coverage
– Ensure that all relevant info is captured
• Concision– Minimize number of features
without sacrificing coverage
• Directness– Ideal features are independently
useful for prediction
Image Intensity
Slide: Derek Hoiem
![Page 13: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/13.jpg)
Image representations
• Templates– Intensity, gradients, etc.
• Histograms– Color, texture, SIFT descriptors, etc.
Slide: Derek Hoiem
![Page 14: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/14.jpg)
Classifiers
Training Labels
Training Images
Classifier Training
Training
Image Features
Trained Classifier
Slide: Derek Hoiem
![Page 15: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/15.jpg)
Learning a classifier
Given some set of features with corresponding labels, learn a function to predict the labels from the features
x x
xx
x
x
x
x
oo
o
o
o
x2
x1Slide: Derek Hoiem
![Page 16: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/16.jpg)
One way to think about it…
• Training labels dictate that two examples are the same or different, in some sense
• Features and distance measures define visual similarity
• Classifiers try to learn weights or parameters for features and distance measures so that visual similarity predicts label similarity
Slide: Derek Hoiem
![Page 17: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/17.jpg)
Slide: Erik Sudderth
![Page 18: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/18.jpg)
Dimensionality Reduction
• PCA, ICA, LLE, Isomap
• PCA is the most important technique to know. It takes advantage of correlations in data dimensions to produce the best possible lower dimensional representation, according to reconstruction error.
• PCA should be used for dimensionality reduction, not for discovering patterns or making predictions. Don't try to assign semantic meaning to the bases.
![Page 19: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/19.jpg)
Many classifiers to choose from• SVM• Neural networks• Naïve Bayes• Bayesian network• Logistic regression• Randomized Forests• Boosted Decision Trees• K-nearest neighbor• RBMs• Etc.
Which is the best one?
Slide: Derek Hoiem
![Page 20: The blue and green colors are actually the same](https://reader035.fdocuments.us/reader035/viewer/2022062803/568147ad550346895db4ec97/html5/thumbnails/20.jpg)
Next Two Lectures:
• Friday we'll talk about clustering methods (k-means, mean shift) and their common usage in computer vision -- building "bag of words” representations inspired by the NLP community. We'll be using these models for projects 2 and 3.
• Monday we'll focus specifically on classification methods, e.g. nearest neighbor, naïve-Bayes, decision trees, linear SVM, Kernel methods. We’ll be using these for projects 3 and 4 (and optionally 2).