**A collection of tutorials and examples for solving and understanding machine learning and pattern classification tasks.**
- Using Python's sci-packages to prepare data for Machine Learning tasks and other data analyses
• Techniques for Dimensionality Reduction
• Projection
• Component Analyses
• Linear Transformation
• Principal Component Analysis (PCA)
• Multiple Discriminant Analysis (MDA)
• Feature Selection
• Sequential Feature Selection Algorithms
• Techniques for Parameter Estimation
• Parametric Techniques
• Introduction to the Maximum Likelihood Estimate (MLE)
• How to calculate Maximum Likelihood Estimates (MLE) for different distributions
• Non-Parametric Techniques
• Kernel density estimation via the Parzen-window technique
• The K-Nearest Neighbor (KNN) technique
• Regression Analysis
• Linear Regression
• Non-Linear Regression
• Statistical Pattern Recognition Examples
• Supervised Learning
• Parametric Techniques
• Univariate Normal Density
• Multivariate Normal Density
• Non-Parametric Techniques
• Unsupervised Learning
#Techniques for Dimensionality Reduction [back to top]
[back to top]
View IPython Notebook
[back to top]
View IPython Notebook
View IPython Notebook
Download PDF
### Parametric Techniques [[back to top](#sections)] ### Introduction to the Maximum Likelihood Estimate (MLE) [[back to top](#sections)]
 ### Maximum Liklihood parameter Estimation (MLE) for different distributions [[back to top](#sections)]
### Kernel density estimation via the Parzen-window technique [[back to top](#sections)]
 #Regression Analysis [[back to top](#sections)] ##Linear Regression [[back to top](#sections)]
##Non-Linear Regression [[back to top](#sections)]
# Statistical Pattern Recognition [[back to top](#sections)] ## Supervised Learning ### Parametric Techniques #### Univariate Normal Density [[back to top](#sections)]
## Example 1 [[back to top](#sections)]
- Statistical Pattern Recognition
- Supervised Learning
- Parametric Learning
- Bayes Decision Theory
- Univariate data
- 2-class problem
- equal variances
- equal priors
- Gaussian model (2 parameters)
- No Risk function
View IPython Notebook
Download PDF
- Statistical Pattern Recognition
- Supervised Learning
- Parametric Learning
- Bayes Decision Theory
- Univariate data
- 2-class problem
- different variances
- equal priors
- Gaussian model (2 parameters)
- No Risk function
View IPython Notebook
Download PDF
- Statistical Pattern Recognition
- Supervised Learning
- Parametric Learning
- Bayes Decision Theory
- Univariate data
- 2-class problem
- equal variances
- different priors
- Gaussian model (2 parameters)
- No Risk function
View IPython Notebook
Download PDF
- Statistical Pattern Recognition
- Supervised Learning
- Parametric Learning
- Bayes Decision Theory
- Univariate data
- 2-class problem
- different variances
- different priors
- Gaussian model (2 parameters)
- With conditional Risk (loss functions)
View IPython Notebook
Download PDF
- Statistical Pattern Recognition
- Supervised Learning
- Parametric Learning
- Bayes Decision Theory
- Univariate data
- 2-class problem
- different variances
- equal priors
- Cauchy model (2 parameters)
- With conditional Risk (1-0 loss functions)
View IPython Notebook
Download PDF
#### Multivariate Normal Density
- Statistical Pattern Recognition
- Supervised Learning
- Parametric Learning
- Bayes Decision Theory
- Multivariate data (2-dimensional)
- 2-class problem
- different variances
- equal prior probabilities
- Gaussian model (2 parameters)
- with conditional Risk (1-0 loss functions)
View IPython Notebook
Download PDF