# Difference between revisions of "Lecture Materials"

From Introduction to Data Science

Dan Lizotte (talk | contribs) (→Lecture Materials: Fixed link to nonlinear models pdf) |
Dan Lizotte (talk | contribs) (Added classification performance evaluation materials) |
||

Line 11: | Line 11: | ||

* Nonlinear Models [ [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/8_Nonlinear%20Models/nonlinear_models.html slides] | [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/8_Nonlinear%20Models/nonlinear_models.Rmd Rmd] | [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/8_Nonlinear%20Models/nonlinear_models.pdf pdf] ] | * Nonlinear Models [ [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/8_Nonlinear%20Models/nonlinear_models.html slides] | [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/8_Nonlinear%20Models/nonlinear_models.Rmd Rmd] | [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/8_Nonlinear%20Models/nonlinear_models.pdf pdf] ] | ||

* Unsupervised Learning [ [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/9_Unsupervised%20Learning/unsupervised-learning.html slides] | [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/9_Unsupervised%20Learning/unsupervised-learning.Rmd Rmd] | [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/9_Unsupervised%20Learning/unsupervised-learning.pdf pdf] ] | * Unsupervised Learning [ [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/9_Unsupervised%20Learning/unsupervised-learning.html slides] | [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/9_Unsupervised%20Learning/unsupervised-learning.Rmd Rmd] | [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/9_Unsupervised%20Learning/unsupervised-learning.pdf pdf] ] | ||

+ | |||

+ | '''Materials with associated video lectures (see OWL)''' | ||

+ | |||

+ | * Classification Performance Evaluation [ [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/10_Classification%20Performance%20Evaluation/classification_performance_evaluation.html slides] | [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/10_Classification%20Performance%20Evaluation/classification_performance_evaluation.Rmd Rmd] | [http://www.csd.uwo.ca/~dlizotte/teaching/cs4414_F17/Lectures/10_Classification%20Performance%20Evaluation/classification_performance_evaluation.pdf pdf] ] | ||

+ | |||

= Previous Offerings = | = Previous Offerings = |

## Revision as of 21:58, 24 November 2017

## Contents

# Lecture Materials

Materials from the most recent run of the course will be posted here. They will be updated as the term progresses.

- Welcome
- Data Preparation [ slides | Rmd | pdf ]
- (Re)introduction to Statistics [ slides | Rmd | pdf]
- Supervised Learning [ slides | Rmd | pdf]
- Performance Evaluation [ slides | Rmd | pdf]
- Model Selection [ slides | Rmd | pdf]
- Classification [ slides | Rmd | pdf]
- Nonlinear Models [ slides | Rmd | pdf ]
- Unsupervised Learning [ slides | Rmd | pdf ]

**Materials with associated video lectures (see OWL)**

# Previous Offerings

## From W17

- Welcome
- Data Preparation [ slides | Rmd | pdf ]
- (Re)introduction to Statistics [ slides | Rmd | pdf]
- Supervised Learning [ slides | Rmd | pdf]
- Linear Models [ slides | Rmd | pdf ]
- Nonlinear Models [ slides | Rmd | pdf ] | html ]
- Unsupervised Learning [ slides | Rmd | pdf | html ]
- Performance Measures and Class Imbalance [ slides | Rmd | pdf | html ]

- Information Visualisation

- Lecture on what I would call "Principles of Information Visualisation"
- Inspiration from the Tableau public gallery. (Recall Tableau is free for students.)

- Feature Selection and Construction
**Video Lectures**by Isabelle Guyon of ClopiNet- Isabelle Guyon on Feature Selection (longer version)
- Isabelle Guyon on Feature Construction (starts at 1:00:00)
- Special issue on features in JMLR
- paper by Guyon et al. on feature selection/construction

## From W16

- Flu trends papers: On OWL

- (Re)introduction to Statistics [ html | Rmd ]
- Supervised Learning [ html | Rmd ]
- Linear Models [ html | Rmd ]
- Nonlinear Models [ html | Rmd
- Unsupervised Learning [ html | Rmd ]
- Visual Analytics
**Guest Lecture**by Arman Didandeh [pdf] - MapReduce
**Guest Lecture**by Hanan Lutfiyya [pdf] - Performance Measures and Class Imbalance [ html | Rmd ]
- Feature Selection and Construction
**Video Lectures**by Isabelle Guyon of ClopiNet- Isabelle Guyon on Feature Selection (longer version)
- Isabelle Guyon on Feature Construction (starts at 1:00:00)
- Course on feature selection/construction
- Special issue on features in JMLR
- paper by Guyon et al. on feature selection/construction

# Tutorials and Summaries

- ggplot2 cheat sheet
- Data Wrangling cheat sheet

# Other Resources

- Materials from Stanford's ML class by Andrew Ng. Excellent notes.

- Bibliography/suggested reading from Colin Cherry's lecture:
- Structured Perceptron
- Michael Collins. Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms. EMNLP 2002. [1]

- Some applications:
- Passive Aggressive Algorithm and MIRA:
- Applications (of MIRA):
- Pegasos
- Shai Shalev-Shwartz, Yoram Singer, and Nathan Srebro. Pegasos: Primal Estimated sub-GrAdient SOlver for SVM. ICML 2007. [8]

- Structured SVM:

- Structured Perceptron

## Previous Incarnations of This Course: CS886 at the University of Waterloo

- Lecture 1 - Intro, Regression
- Lecture 2 - Model Selection, Empirical Evaluation
- Lecture 3,4,5,6 - Logistic Regression, Naive Bayes, SVMs
- Lecture 7 - k-NN and related methods
- Lecture 8 - Decision Trees, Documents
- Lecture 9 - Documents, Images, Clustering, Dimensionality Reduction
- Watch-On-Your-Own - Lectures on feature selection and construction by Isabelle Guyon of ClopiNet
- Isabelle Guyon on Feature Selection (longer version)
- Isabelle Guyon on Feature Construction (starts at 1:00:00)
- Course on feature selection/construction
- Special issue on features in JMLR
- paper by Guyon et al. on feature selection/construction

- Lecture 10 - Introduction to HMMs - Michelle Karg
- Lecture 11 - Machine Learning Words of Wisdom - John Doucette
- Lecture 12 - Scaling Up with Online Learning - Dr. Colin Cherry

### S13

- Lecture 1 - Intro, Regression
- Lecture 2 - Model Selection, Empirical Evaluation
- Lecture 3,4,5 - Logistic Regression, Naive Bayes, SVMs
- Lecture 6 - Learning Theory Light
- Lecture 7 - Documents and Images
- Lecture 8 - Clustering
- Lecture 9 - Sound Features, Dimensionality Reduction
- Lecture 10 - Scaling Up with Online Learning - Dr. Colin Cherry
- Lecture 11 - Data Mining - Luiza Antonie
- Lecture 12 - Introduction to HMMs - Michelle Karg

- Short Lecture 1 - Decision Trees
- Short Lecture 2 - K-Nearest-Neighbours

### EarlierTerms

- Lecture 1 - (F12) - Intro, Regression
- Lecture 2 - (F12) - Overfitting, Performance Evaluation, Cross-Validation
- Lecture 3,4 - (F12) - More Classification: Logistic Regression, Naive Bayes, SVMs
- Lecture 5,6 - (F12) - Non-linear Classifiers: Knn, Decision Trees
- Lecture 6 - (F12) - Learning Theory Light
- Lecture 7 - (F12) - Image Features, Clustering
- Paper on SIFTs + VQ (or Sparse Coding) for classification
- Open-Source SIFT (and other) software
- ECCV Tutorial on Feature Learning for Image Classification. Kai Yu and Andrew Ng

- Lecture 8 - Lectures on feature selection and construction by Isabelle Guyon of ClopiNet
- Isabelle Guyon on Feature Selection (longer version)
- Isabelle Guyon on Feature Construction (starts at 1:00:00)
- Course on feature selection/construction
- Special issue on features in JMLR
- paper by Guyon et al. on feature selection/construction

- Lecture 9 - (F12) - Audio Features, Dimensionality Reduction (PCA)
- Feature extraction from audio and their application in music organization and transient enhancement in recorded music
- Audio Content Search
- Related paper: Martin F. McKinney and Jeroen Breebaart. Features for Audio and Music Classification.

- Lecture 10 by Dr. Kiri Wagstaff
- Lecture 11 by Dr. Michelle Karg
- Lecture 12 by Dr. Colin Cherry - (F12) - See also the bibliography