slide1
Download
Skip this Video
Download Presentation
The blue and green colors are actually the same

Loading in 2 Seconds...

play fullscreen
1 / 20

The blue and green colors are actually the same - PowerPoint PPT Presentation


  • 89 Views
  • Uploaded on

The blue and green colors are actually the same. http://blogs.discovermagazine.com/badastronomy/2009/06/24/the-blue-and-the-green/. 09/19/11. Machine Learning: Overview. Computer Vision James Hays, Brown. Slides: Isabelle Guyon , Erik Sudderth , Mark Johnson, Derek Hoiem.

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about ' The blue and green colors are actually the same' - perry-emerson


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
machine learning overview
09/19/11

Machine Learning: Overview

Computer Vision

James Hays, Brown

Slides: Isabelle Guyon, Erik Sudderth, Mark Johnson,Derek Hoiem

Photo: CMU Machine Learning Department protests G20

machine learning overview1
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.
impact of machine learning
Impact of Machine Learning
  • Machine Learning is arguably the greatest export from computing to other scientific fields.
machine learning applications
Machine Learning Applications

Slide: Isabelle Guyon

image categorization
Image Categorization

Training

Training Labels

Training Images

Image Features

Classifier Training

Trained Classifier

Slide: Derek Hoiem

image categorization1
Image Categorization

Training

Training Labels

Training Images

Image Features

Classifier Training

Trained Classifier

Testing

Prediction

Image Features

Trained Classifier

Outdoor

Test Image

Slide: Derek Hoiem

slide9
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 blahblah“)

example boundary detection
Example: Boundary Detection
  • Is this a boundary?
image features
Image features

Training

Training Labels

Training Images

Image Features

Classifier Training

Trained Classifier

Slide: Derek Hoiem

general principles of representation
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

image representations
Image representations
  • Templates
    • Intensity, gradients, etc.
  • Histograms
    • Color, texture, SIFT descriptors, etc.

Slide: Derek Hoiem

classifiers
Classifiers

Training

Training Labels

Training Images

Image Features

Classifier Training

Trained Classifier

Slide: Derek Hoiem

learning a classifier
Learning a classifier

Given some set of features with corresponding labels, learn a function to predict the labels from the features

x

x

x

x

x

x

x

o

x

o

o

o

o

x2

x1

Slide: Derek Hoiem

one way to think about it
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

dimensionality reduction
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.
many classifiers to choose from
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

next two lectures
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).
ad