MACHINE LEARNING

Machine Learning course for Data Professionals using R, Python and Spark. This course covers topics such as fundamentals of Machine Learning, Research Analytics, along with implementation of Machine Learning principle using R, Python and Spark.
COURSE OBJECTIVE:
This Machine Learning course has been designed for Data Professionals to understand, represent and predict data more accurately. One will be able to use his/her existing talents with computing knowledge into Machine Learning Analysts having the capability of utilizing Machine Learning productively. Fundamentals of Machine Learning, Research Analytics, along with implementation of Machine Learning principle using R, Python and Spark, are covered in this course.

LESSON PLANS


​COURSE A: FUNDAMENTALS OF MACHINE LEARNING
SESSION 1: FUNDAMENTALS OF MACHINE LEARNING:
Session Goal:
  • Understanding Machine learning objectives.
  • Data dimensions in Machine learning.
  • Fundamentals of Algorithms and mapping from Input and Output.
  • Parametric and Nonparametric Machine Learning algorithms.
  • Supervised, Unsupervised and Semi-Supervised Learning.
  • Estimating overfitting and underfitting.

SESSION 2: MATH BEHIND MACHINE LEARNING:
Session Goal:
  • Linear Algebra fundamentals.
  • Understanding Matrices and Vectors.
  • Addition and Scalar Multiplication.
  • Multiplication variants and Inverse, Transpose.
  • Linear Regression with One and Multiple Variables.

SESSION 3: FUNDAMENTALS OF MATLABS/R PRACTICAL IMPLEMENTATION:
Session Goal:
  • Applying basic operation.
  • Playing with data.
  • Computation.
  • Using Control Statements.
  • Plotting data.
  • Vectorization and Linear Regression.

​SESSION 4: MACHINE LEARNING ALGORITHMS:
Session Goal:
  • Algorithm classification.
  • Decision Trees.
  • Naïve Bayes Classification.
  • Least Square Regression.
  • Logistic Regression.
  • SVM: Support Vector machine.
  • Ensemble Methods.
  • Clustering Algorithms.
  • PCA: Principal Component Analysis.
  • SVD: Singular Value Decomposition.
  • ICA: Independent Component Analysis.

SESSION 4: APPLYING MACHINE LEARNING:
Session Goal:
  • Applying Machine Learning Algorithm in Software development.
  • Applying Machine Learning Algorithm to software fault Tolerance.
  • Case study: Stock Trading.

COURSE B: RESEARCH ANALYTICS
SESSION 1: RESEARCH ANALYSIS FUNDAMENTALS:
Session Goal:
  • Understanding Concept of Data in Research Analytics.
  • Research Process and Data.
  • Types of Data.
  • Statistical Software for Data Analysis.

SESSION 2: RELIABILITY AND VALIDITY ANALYSIS:
Session Goal:
  • Concept of Validity and Reliability.
  • Internal and Inter-Rater Reliability using Kappa Statistics.
  • Content and Construct Validity.
  • Internal, External and Criterion Validity.
  • Testing with CFA and AMOS.

SESSION 3: DATA CLEANING, IMPUTATION AND OUTLIER TESTING:
Session Goal:
  • Concept of Data Cleaning and Data Imputation.
  • Outlier Testing Identification and Treatment.
  • Using SPSS: Data view, Variable view and operations.
  • Working with SPSS commands.

SESSION 4: HYPOTHESIS TESTING AND TEST OF DIFFERENCE:
Session Goal:
  • Hypothesis and its Types.
  • Concept and Decision Rules for Hypothesis Testing.
  • One-Sample T-Test and Independent-Samples T-Test.
  • Paired-Samples T-Test.

SESSION 5: DESCRIPTIVE STATISTICS, CORRELATION AND REGRESSION ANALYSIS:
Session Goal:
  • Frequency Distribution.
  • Measure of central Tendency and Distribution Analysis.
  • Measure of Dispersion.
  • Concept of Correlation Analysis: Co-variance ,Non-parametric and Partial Correlation.
  • Concept of Regression Analysis :Dependency ,Assumptions, Diagnostics.

​COURSE C: IMPLEMENTING MACHINE LEARNING PRINCIPLE USING R
SESSION 1: INTRODUCING R:
Session Goal:
  • Download and Install R.
  • Use R console and R studio.
  • Fundamentals of R instructions.
  • Data sets in R.
  • Managing R Objects: workspace, data, manipulations and representation.

SESSION 2: OPERATORS AND FUNCTIONS IN R:
Session Goal:
  • Arithmetic, Logical and other operators in R.
  • Operator precedence.
  • Basic understanding of function.
  • Mathematical functions.
  • Differentiation and Integration.

SESSION 3: FUNDAMENTALS OF R GRAPHICS AND SUBSCRIPTING:
Session Goal:
  • Understanding High Level plotting instruction.
  • Interactive communication with graphs.
  • 3D graphics.
  • Subscripting with vectors, matrices.
  • Extraction: lists and dataframes.
  • Combining: vectors,matrices,lists and dataframes.
  • Rearranging: Elements in Matrix.

​SESSION 4: WRITING FUNCTIONS IN R:
Session Goal:
  • Writing a new function.

  • Object Check and Name clashes.
  • Returning multiple values.
  • Local Variables and evaluation environment.
  • Working with variable number of arguments.
  • Lazy evaluation and dynamic loading of external routines.

SESSION 5: READING DATA FILES INTO R AND PRINTING USING FORMATTING:
Session Goal:
  • Reading Microsoft Excel files into R.
  • Reading diversified formats.
  • Sending output to a file and Writing R Objects for transport.
  • Using history.
  • Command reediting ,Customized printing.
  • Communicating with OS.
  • Dynamic 3D graphics in R.

SESSION 6: VECTORIZED PROGRAMMING AND MAPPING FUNCTIONS:
Session Goal:
  • Mapping functions to a matrix, vectors, dataframes and lists.
  • Using functions: mapply, rapply, vectorize and tapply
    Working with Loops.
  • Calling functions with argument lists.
  • OOPS in R.
  • Recursion.
  • Error management.

SESSION 7: STATISTICAL MODELING WITH R:
Session Goal:
  • Understanding Data for statistical models.
  • Expressing a statistical model in R.
  • Using statistical modeling Objects.
  • Exploring functions glm, gam, loess, rpart, nls.
  • Normal quantile plot and coplot.
  • Analysis of Variance and covariance.
  • Regression diagnostics and Experimental design.
  • Optimization.

SESSION 8: BIG DATA ANALYTICS:
Session Goal:
  • Analytical Big Data and Operational Big Data Frameworks.
  • Hadoop 2.0 Architecture.
  • NoSql principles and data modeling Techniques.
  • Using R with Hadoop and NoSql.
  • Case study illustrating Hadoop/NoSQL and R together.
  • Spark ML introduction and Benefits.

COURSE D: IMPLEMENTING MACHINE LEARNING PRINCIPLE USING PYTHON
SESSION 1: FUNDAMENTALS OF PYTHON:
Session Goal:
  • Understanding Python features.
  • Working with input and output.
  • Error Handling.
  • Understanding function protocols.
  • Working with Python data structures.
  • Creating and using Python scheme using libraries and packages.
  • Python Architecture.
  • Working with Libraries like shutil, tempfile, subprocess, glob, sys, unites and others.

SESSION 2: WORKING WITH STATISTICS AND PROBABILITY USING PYTHON:
Session Goal:
  • Understanding data.
  • Using Mean, median, Mode in Python.
  • Working with Variation and standard Deviation using Python.
  • Data Distribution.
  • Covariance and Correlation.
  • Working with Conditional Probability.
  • Implementing Bayes Theorem.

SESSION 3: MACHINE LEARNING WITH PYTHON: PART 1:
Session Goal:
  • Supervised and Unsupervised Learning.
  • Using Train/Test for Polynomial Regression.
  • Implementing Bayesian Methods.
  • K-Mean clustering.
  • Working with Decision Tree using Python.
  • Using Support Vector Machine.

SESSION 4: MACHINE LEARNING WITH PYTHON: PART 2:
Session Goal:
  • KNN concept and Implementation.
  • Principal of Component Analysis.

COURSE E: IMPLEMENTING MACHINE LEARNING PRINCIPLE USING SPARK
SESSION 1: FUNDAMENTALS OF SPARK - 1:
Session Goal:
  • Introducing Spark.
  • Identifying Spark Features.
  • Components of Spark.
  • Installation and Architecture of Spark.
  • RDD Principles.

SESSION 2: FUNDAMENTALS OF SPARK - 2:
Session Goal:
  • Spark RDD in Depth.
  • SparkSQL and DataFrames Basics.
  • Spark Job Execution.
  • Introduction to Spark Machine Learning.

SESSION 3: IMPLEMENTING MACHINE LEARNING ALGORITHMS IN SPARK -1:
Session Goal:
  • Fundamentals of ML math.
  • Classification and Regression: Decision tree, Naïve Bayes.
  • Clustering: K-mean.
  • Reduction: SVD and PCA.

SESSION 4: IMPLEMENTING MACHINE LEARNING ALGORITHMS IN SPARK -2:
Session Goal:
  • Collaborative filtering.
  • Feature Extraction and transformation.
  • PMML Model export.
  • Optimization.
CASE STUDY AND PROJECTS:
Case studies are Integral part of Training. As part of this course we will ensure you implement Real-time case studies ​in various domains which includes:
  1. Banking.
  2. Telecom
  3. Ecommerce.
  4. HealthCare.​
​These case studies will be evaluated by domain experts and you would get an opportunity to get Feedback on the work.
TRAINING FEATURES:
1) Extensive Real Time Live Examples, Projects & POCs for improved practical competency, ensure deployment readiness and implementation.
2) Custom Lab, Software and Environment provided with Real-time Project Simulation.
3) Recorded Videos complemented with corresponding lecture ppts, materials & lab guides. (Provided in the form of MP4 videos, pdf, ppt for offline access as well).
4) Certification and Job-Interview Counselling & Coaching after every training.​