Machine Learning with R

BACK
Machine learning

 Differentiating algorithmic and model based frameworks, Bias-variance Dichotomy, Model Validation Approaches.
 Supervised Learning with Regression and Classification techniques
 Regression:
 Ordinary Least Squares, Ridge Regression, Lasso Regression,
 Classification:
 Logistic Regression, K Nearest Neighbours Regression & Classification,
 Bayes Rule and Classification Problem,Linear Discriminant Analysis,
 Quadratic Discriminant Analysis:
 Decision Trees:
 Regression and Classification Trees Bagging, Boosting 
 Ensemble Methods, Random Forest, Bootstrap.
 Neural networks:
 Introduction, Single Layer Perception.
 Multi-layer Perception Forward Feed and backward propagation.
 Support Vector Machine:
  • Maximum Marginal Classifier,
  • Support Vector Classifier,
  • Support Vector Machine,
  • SVMs with More than Two Classes
 Unsupervised learning:
  • Principle component analysis, clustering methods, K-means clustering, Hierarchical clustering, Meloid Cluster Analysis
  • Dimensionality Reduction, Principal Component Analysis, Association rules
  • Market Basket Analysis.

Introduction to R

R Syntax:  A gentle introduction to R expressions, variables, and functions
Vectors:  Grouping values into vectors, then doing arithmetic and graphs with them
Matrices:  Creating and graphing two-dimensional data sets
Summary Statistics:  Calculating and plotting some basic statistics: mean, median, and standard deviation
Factors: Creating and plotting categorized data
Data Frames: Organizing values into data frames, loading frames from files and merging them
Working With Real-World Data: Testing for correlation between data sets, linear models and installing additional packages
 Probability distributions R as a set of statistical tables, Examining the distribution of a set of data, Oneand two-sample tests, Grouping,
    loops and conditional execution , Grouped expressions, Control statements , Conditional execution: if statements
 Repetitive execution: for loops, repeat and while
 Writing your own functions Simple examples, Defining new binary operators, Named arguments and defaults, The ‘…’ argument,
    Assignments within functions More advanced examples, efficiency factors in block designs Dropping all names in a printed 
    array, Recursive numerical integration Scope, Customizing the environment, Classes, generic functions and Object orientation.
 Statistical models in R
Defining statistical models; formulae , Contrasts, Linear models, Generic functions for extracting model information, Analysis of variance and model comparison ,ANOVA tables, Updating fitted models, Generalized linear models , Families, The glm() function, Nonlinear least squares and maximum likelihood models , Least squares, Maximum likelihood, Some non-standard models, Graphical procedures
,High-level plotting commands,The plot() function, Displaying multivariate data, Display graphics, Arguments to high-level plotting
functions, Interacting with graphics, Using graphics parameters, Permanent changes: The par() function, Temporary changes: Arguments to graphics functions, Graphical elements, Packages , Standard packages, Contributed packages and CRAN 


 Ensemble Methods, Random Forest, Bootstrap.
 Neural networks:
 Introduction, Single Layer Perception.
 Multi-layer Perception Forward Feed and backward propagation.
 Support Vector Machine:
  • Maximum Marginal Classifier, Support Vector Classifier, Support Vector Machine, SVMs with More than Two Classes
 Unsupervised learning:
  • Principle component analysis, clustering methods, K-means clustering, Hierarchical clustering, Meloid Cluster Analysis
  • Dimensionality Reduction, Principal Component Analysis, Association rules
  • Market Basket Analysis.