Machine Learning Engineer Masters Program

 Introduction to Python

Goal: Give a brief idea of what Python is and touch on the basics.

Learning Objectives: At the end of this Module, you should be able to:

• Define Python
• Understand the need for Programming
• Know why to choose Python over other languages
• Setup Python environment
• Understand Various Python concepts – Variables, Data Types Operators, Conditional Statements and Loops
• Illustrate String formatting
• Understand Command Line Parameters and Flow control

Topics:

• Overview of Python
• Companies using Python
• Other applications in which Python is used
• Discuss Python Scripts on UNIX/Windows
• Variables
• Operands and Expressions
• Conditional Statements
• Loops
• Command Line Arguments
• Writing to the screen

Hands-on/Demo:

• Creating “Hello World” code
• Variables
• Demonstrating Conditional Statements
• Demonstrating Loops

 Sequences and File Operations

Goal: Learn different types of sequence structures, related operations, and their usage. Also learn diverse ways of opening, reading, and writing to files.

Learning Objectives: At the end of this Module, you should be able to:

• Understand Operations performed on Files
• Learn what Sequences are
• Execute Sequence Operations
• Understand Types of Sequences in Python: Lists, Tuples, Strings, Sets, Dictionaries

Topics:

• Python files I/O Functions
• Lists and related operations
• Tuples and related operations
• Strings and related operations
• Sets and related operations
• Dictionaries and related operations

Hands-on/Demo:

• Tuple - properties, related operations, compared with a list
• List - properties, related operations
• Dictionary - properties, related operations
• Set - properties, related operations

 Deep Dive – Functions and OOPs

Goal: In this Module, you will learn how to create user-defined functions and different Object Oriented Concepts like Inheritance, Polymorphism, Overloading etc.

Learning Objectives: At the end of this Module, you should be able to:

• Define and call Functions
• Understand why the return statement is used
• Understand and execute Object-Oriented Concepts

Topics:

• Functions
• Function Parameters
• Global variables
• Variable scope and Returning Values
• Lambda Functions
• Object-Oriented Concepts

Hands-on/Demo:

• Functions - syntax, arguments, keyword arguments, return values
• Lambda - features, syntax, options, compared with the functions

 Working with Modules and Handling Exceptions

Goal: In this Module, you will learn how to create generic python scripts, how to address errors/exceptions in code and finally how to extract/filter content using regex.

Learning Objectives: At the end of this Module, you should be able to:

• Use Standard Libraries
• Use Modules
• Understand Exception Handling
• Create User Defined Exceptions

Topics:

• Standard Libraries
• Modules Used in Python (OS, Sys, Date and Time etc.)
• The Import statements
• Module search path
• Package installation ways
• Errors and Exception Handling
• Handling multiple exceptions

Hands-on/Demo:

• Errors and exceptions - types of issues, remediation
• Packages and module - modules, import options, sys path

 Introduction to NumPy & Pandas

Goal: This Module helps you get familiar with the basics of statistics, different types of measures and probability distributions, and the supporting libraries in Python that assist in these operations.

Learning Objectives: At the end of this Module, you should be able to:

• Create arrays using NumPy
• Use NumPy to perform mathematical operations on arrays
• Read and write data from text/CSV files into arrays and vice-versa
• Understand Pandas and employ it for data manipulation
• Understand and use the data structures available in Pandas
• Read and write data between files and programs

Topics:

• NumPy - arrays
• Operations on arrays
• Indexing slicing and iterating
• Reading and writing arrays on files
• Pandas - data structures & index operations
• Reading and Writing data from Excel/CSV formats into Pandas

Hands-on/Demo:

• NumPy library- Installation, Creating NumPy array, operations performed on NumPy array
• Pandas library- Installation, creating series and data frames, Importing and exporting data

 Data Visualisation

Goal: In this Module, you will learn in detail about data visualization.

Learning Objectives: At the end of this Module, you should be able to:

• Create simple plots like scatter plot, histogram, bar graph, pie chart using Matplotlib
• Add different styles to the plot
• Use the different forms of plots available in Matplotlib

Topics:

• matplotlib library
• Grids, axes, plots
• Markers, colours, fonts and styling
• Types of plots - bar graphs, pie charts, histograms
• Contour plots

Hands-on/Demo:

• Matplotlib - Installation, Using Scatterplot, histogram, bar graph, pie chart to show information, Styling of Plot

 Data Manipulation

Goal: Through this Module, you will understand in detail about Data Manipulation.

Learning Objectives: At the end of this Module, you should be able to:

• Perform function manipulations on Data objects
• Perform Concatenation, Merging and Joining on DataFrames
• Iterate through DataFrames
• Explore Datasets and extract insights from it

Topics:

• Basic Functionalities of a data object
• Merging of Data objects
• Concatenation of data objects
• Types of Joins on data objects
• Exploring a Dataset
• Analyzing a dataset

Hands-on/Demo:

• Pandas Function- Ndim(), axes(), values(), head(), tail(), sum(), std(), iteritems(), iterrows(), itertuples(), GroupBy operations, Aggregation, Concatenation, Merging and joining

 GUI Programming

This module is a combination of Live Instructor-Led Training and Self-paced learning. 

Goal: In this module, you will learn GUI programming using ipywidgets package.

Learning Objectives: After completing this module, you should be able to:

• Learn ipywidgets package
• Understand different widgets like Numeric Widgets, Boolean Widgets, Selection Widgets, String Widgets, Date Picker, Color Picker and Container Widgets
• Create an application using ipywidgets package

Topics:

• Ipywidgets package
• Numeric Widgets
• Boolean Widgets
• Selection Widgets
• String Widgets
• Date Picker
• Color Picker
• Container Widgets
• Creating a GUI Application

Hands-on/Demo:

• Create GUI

Self-paced Concept: Network Programming and Multithreading

Goal: In this module, you will learn how to connect your server with MySQL DB. In addition, learn about Socket programming.

Learning Objectives: After completing this module, you should be able to:

• Understand the concept of Database
• Access MySQL DB
• Create socket for sending short messages
• Learn Multithreading concepts

Topics:

• MySQL DB access
• Network programming
• Multithreading

Hands-on/Demo:

• Database Creation
• CRUD Operations
• Network Creation
• Multithreading

 Developing Web Maps and Representing information using Plots (Self-paced)

This module is Self Paced 

Goal: Throughout this Module, you will be designing Python Applications.

Learning Objectives: At the end of this Module, you should be able to:

• Design a Web Map using Folium and Pandas for displaying Volcanoes in USA and Population in different countries in a Single map Represent information from Dataset with the help of Plots

Topics:

• Use of Folium Library
• Use of Pandas Library
• Flowchart of Web Map application
• Developing Web Map using Folium and Pandas
• Reading information from Dataset and represent it using Plots

 Computer vision using OpenCV and Visualisation using Bokeh (Self-paced)

This module is Self Paced 

Goal: Throughout this Module, you will be designing Python Applications.

Learning Objectives: At the end of this Module, you should be able to:

• Perform Web Scraping using Python
• Visualise Data on the browser using Bokeh
• Use OpenCV to create a motion detection software

Topics:

• Beautiful Soup Library
• Requests Library
• Scrap all hyperlinks from a webpage, using Beautiful Soup & Requests
• Plotting charts using Bokeh
• Plotting scatterplots using Bokeh
• Image Editing using OpenCV
• Face detection using OpenCV
• Motion Detection and Capturing Video

 Introduction to Data Science

Goal: Get an introduction to Data Science in this Module and see how Data Science helps to analyze large and unstructured data with different tools.

 Objectives: At the end of this Module, you should be able to:

• Define Data Science
• Discuss the era of Data Science
• Describe the Role of a Data Scientist
• Illustrate the Life cycle of Data Science
• List the Tools used in Data Science
• State what role Big Data and Hadoop, Python, R and Machine Learning play in Data Science

 Topics:

• What is Data Science?
• What does Data Science involve?
• Era of Data Science
• Business Intelligence vs Data Science
• Life cycle of Data Science
• Tools of Data Science
• Introduction to Python

 Data Extraction, Wrangling, & Visualization

Goal: Discuss the different sources available to extract data, arrange the data in structured form, analyze the data, and represent the data in a graphical format.

 Objectives: At the end of this Module, you should be able to:

• Discuss Data Acquisition techniques
• List the different types of Data
• Evaluate Input Data
• Explain the Data Wrangling techniques
• Discuss Data Exploration

 Topics:

• Data Analysis Pipeline
• What is Data Extraction
• Types of Data
• Raw and Processed Data
• Data Wrangling
• Exploratory Data Analysis
• Visualization of Data

 Hands-On/Demo:

• Loading different types of dataset in Python
• Arranging the data
• Plotting the graphs

 Introduction to Machine Learning with Python

Goal: In this module, you will learn the concept of Machine Learning and it’s types.

 Objective: At the end of this module, you should be able to:

• Essential Python Revision
• Necessary Machine Learning Python libraries
• Define Machine Learning
• Discuss Machine Learning Use cases
• List the categories of Machine Learning
• Illustrate Supervised Learning Algorithms
• Identify and recognize machine learning algorithms around us
• Understand the various elements of machine learning algorithm like parameters, hyper parameters, loss function and optimization.

 Topics:

• Python Revision (numpy, Pandas, scikit learn, matplotlib)
• What is Machine Learning?
• Machine Learning Use-Cases
• Machine Learning Process Flow
• Machine Learning Categories
• Linear regression
• Gradient descent

 Hands On:

• Linear Regression – Using Boston Dataset

 Supervised Learning - I

Goal: In this module, you will learn Supervised Learning Techniques and their implementation, for example, Decision Trees, Random Forest Classifier etc.

 Objective: At the end of this module, you should be able to:

• Understand What is Supervised Learning?
• Illustrate Logistic Regression
• Define Classification
• Explain different Types of Classifiers such as Decision Tree and Random Forest

 Topics:

• What is Classification and its use cases?
• What is Decision Tree?
• Algorithm for Decision Tree Induction
• Creating a Perfect Decision Tree
• Confusion Matrix
• What is Random Forest?

 Hands On:

• Implementation of Logistic regression, Decision tree, Random forest

 Dimensionality Reduction

Goal: In this module you will learn about impact of dimensions within data. You will be taught to perform factor analysis using PCA and compress dimensions. Also, you will be developing LDA model.  

 Objective: At the end of this module, you should be able to:

• Define the importance of Dimensions
• Explore PCA and its implementation
• Discuss LDA and its implementation

 Topics:

• Introduction to Dimensionality
• Why Dimensionality Reduction
• PCA
• Factor Analysis
• Scaling dimensional model
• LDA

 Hands On:

• PCA
• Scaling

 Supervised Learning - II

Goal: In this module, you will learn Supervised Learning Techniques and their implementation, for example, Decision Trees, Random Forest Classifier etc.

 Objective: At the end of this module, you should be able to:

• Understand What is Naïve Bayes Classifier
• How Naïve Bayes Classifier works?
• Understand Support Vector Machine
• Illustrate How Support Vector Machine works?
• Hyperparameter optimization

 Topics:

• What is Naïve Bayes?
• How Naïve Bayes works?
• Implementing Naïve Bayes Classifier
• What is Support Vector Machine?
• Illustrate how Support Vector Machine works?
• Hyperparameter optimization
• Grid Search vs Random Search
• Implementation of Support Vector Machine for Classification

 Hands On:

• Implementation of Naïve Bayes, SVM

 Unsupervised Learning

Goal: In this module, you will learn about Unsupervised Learning and the various types of clustering that can be used to analyze the data.

 Objective: At the end of this module, you should be able to:

• Define Unsupervised Learning
• Discuss the following Cluster Analysis

       o  K - means Clustering 

       o  C - means Clustering 

       o  Hierarchical Clustering

 Topics:

• What is Clustering & its Use Cases?
• What is K-means Clustering?
• How K-means algorithm works?
• How to do optimal clustering
• What is C-means Clustering?
• What is Hierarchical Clustering?
• How Hierarchical Clustering works?

 Hands On:

• Implementing K-means Clustering
• Implementing Hierarchical Clustering

 Association Rules Mining and Recommendation Systems

Goal: In this module, you will learn Association rules and their extension towards recommendation engines with Apriori algorithm.

 Objective: At the end of this module, you should be able to:

• Define Association Rules
• Learn the backend of recommendation engines and develop your own using python

 Topics:

• What are Association Rules?
• Association Rule Parameters
• Calculating Association Rule Parameters
• Recommendation Engines
• How Recommendation Engines work?
• Collaborative Filtering
• Content Based Filtering

 Hands On:

• Apriori Algorithm
• Market Basket Analysis

 Reinforcement Learning

Goal: In this module, you will learn about developing a smart learning algorithm such that the learning becomes more and more accurate as time passes by. You will be able to define an optimal solution for an agent based on agent environment interaction.

 Objective: At the end of this module, you should be able to

• Explain the concept of Reinforcement Learning
• Generalize a problem using Reinforcement Learning
• Explain Markov’s Decision Process
• Demonstrate Q Learning

 Topics:

• What is Reinforcement Learning
• Why Reinforcement Learning
• Elements of Reinforcement Learning
• Exploration vs Exploitation dilemma
• Epsilon Greedy Algorithm
• Markov Decision Process (MDP)
• Q values and V values
• Q – Learning
• α values

 Hands On:

• Calculating Reward
• Discounted Reward
• Calculating Optimal quantities
• Implementing Q Learning
• Setting up an Optimal Action

 Time Series Analysis

Goal: In this module, you will learn about Time Series Analysis to forecast dependent variables based on time. You will be taught different models for time series modelling such that you analyse a real time dependent data for forecasting.

Objective: At the end of this module, you should be able to:

• Explain Time Series Analysis (TSA)
• Discuss the need of TSA
• Describe ARIMA modelling
• Forecast the time series model

 Topics:

• What is Time Series Analysis?
• Importance of TSA
• Components of TSA
• White Noise
• AR model
• MA model
• ARMA model
• ARIMA model
• Stationarity
• ACF & PACF

 Hands on:

• Checking Stationarity
• Converting a non-stationary data to stationary
• Implementing Dickey Fuller Test
• Plot ACF and PACF
• Generating the ARIMA plot
• TSA Forecasting

 Model Selection and Boosting

Goal: In this module, you will learn about selecting one model over another. Also, you will learn about Boosting and its importance in Machine Learning. You will learn on how to convert weaker algorithms to stronger ones.

 Objective: At the end of this module, you should be able to:

• Discuss Model Selection
• Define Boosting
• Express the need of Boosting
• Explain the working of Boosting algorithm

 Topics:

• What is Model Selection?
• Need of Model Selection
• Cross – Validation
• What is Boosting?
• How Boosting Algorithms work?
• Types of Boosting Algorithms
• Adaptive Boosting

 Hands on:

• Cross Validation
• AdaBoost

 In-Class Project

Goal: In this module, you will learn how to approach and implement a Project end to end, and a Subject Matter Expert will share his experience and insights from the industry to help you kickstart your career in this domain. Finally, we will be having a Q&A and doubt clearing session.

 Objectives: At the end of this module, you should be able to:

• How to approach a project
• Hands-On project implementation
• What Industry expects
• Industry insights for the Machine Learning domain
• QA and Doubt Clearing Session

 Introduction to Graphical Model

Goal:

•  To give a brief idea about Graphical models, graph theory, probability theory, components of graphical models, types of graphical models, representation of graphical models, Introduction to inference, learning and decision making in Graphical Models.

Topics:

• Why do we need Graphical Models?
• Introduction to Graphical Model
• How does Graphical Model help you deal with uncertainty and complexity?
• Types of Graphical Models
• Graphical Modes
• Components of Graphical Model
• Representation of Graphical Models
• Inference in Graphical Models
• Learning Graphical Models
• Decision theory
• Applications

 Bayesian Network

Goal:

•  To give a brief idea of Bayesian networks, independencies in Bayesian Networks and building a Bayesian networks.

Topics:

• What is Bayesian Network?
• Advantages of Bayesian Network for data analysis
• Bayesian Network in Python Examples
• Independencies in Bayesian Networks
• Criteria for Model Selection
• Building a Bayesian Network

 Markov’s Networks

Goal:

•  To give a brief understanding of Markov’s networks, independencies in Markov’s networks, Factor graph and Markov’s decision process.

Topics:

• Example of a Markov Network or Undirected Graphical Model
• Markov Model
• Markov Property
• Markov and Hidden Markov Models
• The Factor Graph
• Markov Decision Process
• Decision Making under Uncertainty
• Decision Making Scenarios

 Inference

Goal:

•  To understand the need for inference and interpret inference in Bayesian and Markov’s Networks.

Topics:

• Inference
• Complexity in Inference
• Exact Inference
• Approximate Inference
• Monte Carlo Algorithm
• Gibb’s Sampling
• Inference in Bayesian Networks

 Model Learning

Goal:

•  To understand the Structures and Parametrization in graphical Models.

Topics:

• General Ideas in Learning
• Parameter Learning
• Learning with Approximate Inference
• Structure Learning
• Model Learning: Parameter Estimation in Bayesian Networks
• Model Learning: Parameter Estimation in Markov Networks

Learning Objectives: In this module, you will learn about developing a smart learning algorithm such that the learning becomes more and more accurate as time passes by. You will be able to define an optimal solution for an agent based on agent-environment interaction. 

 Topics:

• What is Reinforcement Learning
• Why Reinforcement Learning
• Elements of Reinforcement Learning
• Exploration vs Exploitation dilemma
• Epsilon Greedy Algorithm
• Markov Decision Process (MDP)
• Q values and V values
• Q – Learning
• α values

 Hands-On/Demo:

• Calculating Reward
• Discounted Reward
• Calculating Optimal quantities
• Implementing Q Learning
• Setting up an Optimal Action

Skills:

• Implement Reinforcement Learning using python
• Developing Q Learning model in python

 Introduction to Text Mining and NLP

Learning Objectives: In this module, you will learn about text mining and the ways of extracting and reading data from some common file types including NLTK corpora 

 Topics:

• Overview of Text Mining
• Need of Text Mining
• Natural Language Processing (NLP) in Text Mining
• Applications of Text Mining
• OS Module
• Reading, Writing to text and word files
• Setting the NLTK Environment
• Accessing the NLTK Corpora

 Hands On/Demo:

• Install NLTK Packages using NLTK Downloader
• Accessing your operating system using the OS Module in Python
• Reading & Writing .txt Files from/to your Local
• Reading & Writing .docx Files from/to your Local
• Working with the NLTK Corpora

 Extracting, Cleaning and Pre-processing Text

Learning Objectives: This module will help you understand some ways of text extraction and cleaning using NLTK. 

 Topics:

• Tokenization
• Frequency Distribution
• Different Types of Tokenizers
• Bigrams, Trigrams & Ngrams
• Stemming
• Lemmatization
• Stopwords
• POS Tagging
• Named Entity Recognition

 Hands On/Demo:

• Tokenization: Regex, Word, Blank line, Sentence Tokenizers
• Bigrams, Trigrams & Ngrams
• Stopword Removal
• POS Tagging
• Named Entity Recognition (NER)

 Analyzing Sentence Structure

Learning Objective: In this Module, you will learn how to analyse a sentence structure using a group of words to create phrases and sentences using NLP and the rules of English grammar 

 Topics:

• Syntax Trees
• Chunking
• Chinking
• Context Free Grammars (CFG)
• Automating Text Paraphrasing

 Hands On/Demo:

• Parsing Syntax Trees
• Chunking
• Chinking
• Automate Text Paraphrasing using CFG’s

 Text Classification - I

Learning Objective: In this module, you will explore text classification, vectorization techniques and processing using scikit-learn 

 Topics:

• Machine Learning: Brush Up
• Bag of Words
• Count Vectorizer
• Term Frequency (TF)
• Inverse Document Frequency (IDF)

 Hands On/Demo:

• Demonstrate Bag of Words Approach
• Working with CountVectorizer()
• Using TF & IDF

 Text Classification - II

Learning Objective: In this module, you will learn to build a Machine Learning classifier for text classification 

 Topics:

• Converting text to features and labels
• Multinomial Naiive Bayes Classifier
• Leveraging Confusion Matrix

 Hands On/Demo:

• Converting text to features and labels
• Demonstrate text classification using Multinomial NB Classifier
• Leveraging Confusion Matrix

 In Class Project

Goal: In this module, you will learn Sentiment Classification on Movie Rating Dataset 

 Objective: At the end of this module, you should be able to:

• Implement all the text processing techniques starting with tokenization
• Express your end to end work on Text Mining
• Implement Machine Learning along with Text Processing

 Hands-On:

• Sentiment Analysis

 Introduction to Deep Learning

Learning Objectives:

In this module, you’ll get an introduction to Deep Learning and understand how Deep Learning solves problems which Machine Learning cannot. Understand fundamentals of Machine Learning and relevant topics of Linear Algebra and Statistics.

 Topics:

• Deep Learning: A revolution in Artificial Intelligence
• Limitations of Machine Learning
• What is Deep Learning?
• Advantage of Deep Learning over Machine learning
• 3 Reasons to go for Deep Learning
• Real-Life use cases of Deep Learning
• Review of Machine Learning: Regression, Classification, Clustering, Reinforcement Learning, Underfitting and Overfitting, Optimization

Hands-On

• Implementing a Linear Regression model for predicting house prices from Boston dataset
• Implementing a Logistic Regression model for classifying Customers based on a Automobile purchase dataset

 Understanding Neural Networks with TensorFlow

Learning Objectives: 

In this module, you’ll get an introduction to Neural Networks and understand it’s working i.e. how it is trained, what are the various parameters considered for its training and the activation functions that are applied.

Topics:

• How Deep Learning Works?
• Activation Functions
• Illustrate Perceptron
• Training a Perceptron
• Important Parameters of Perceptron
• What is TensorFlow?
• TensorFlow code-basics
• Graph Visualization
• Constants, Placeholders, Variables
• Creating a Model
• Step by Step - Use-Case Implementation

Hands-On

• Building a single perceptron for classification on SONAR dataset

 Deep dive into Neural Networks with TensorFlow

Learning Objectives:

 In this module, you’ll understand backpropagation algorithm which is used for training Deep Networks. You will know how Deep Learning uses neural network and backpropagation to solve the problems that Machine Learning cannot.

 Topics:

•  Understand limitations of a Single Perceptron
• Understand Neural Networks in Detail
• Illustrate Multi-Layer Perceptron
• Backpropagation – Learning Algorithm
• Understand Backpropagation – Using Neural Network Example
• MLP Digit-Classifier using TensorFlow
• TensorBoard

Hands-On

• Building a multi-layered perceptron for classification of Hand-written digits

 Master Deep Networks

Learning Objectives:

In this module, you’ll get started with the TensorFlow framework. You will understand how it works, its various data types & functionalities. In addition, you will create an image classification model.

 Topics:

•  Why Deep Networks
• Why Deep Networks give better accuracy?
• Use-Case Implementation on SONAR dataset
• Understand How Deep Network Works?
• How Backpropagation Works?
• Illustrate Forward pass, Backward pass
• Different variants of Gradient Descent
• Types of Deep Networks

Hands-On

• Building a multi-layered perceptron for classification on SONAR dataset

 Convolutional Neural Networks (CNN)

Learning Objectives:

 In this module, you’ll understand convolutional neural networks and its applications. You will learn the working of CNN, and create a CNN model to solve a problem.

 Topics:

• Introduction to CNNs
• CNNs Application
• Architecture of a CNN
• Convolution and Pooling layers in a CNN
• Understanding and Visualizing a CNN

Hands-On:

• Building a convolutional neural network for image classification. The model should predict the difference between 10 categories of images.

 Recurrent Neural Networks (RNN)

Learning Objectives:In this module, you’ll understand Recurrent Neural Networks and its applications. You will understand the working of RNN, how LSTM are used in RNN, what is Recursive Neural Tensor Network Theory, and finally you will learn to create a RNN model.

 Topics:

• Introduction to RNN Model
• Application use cases of RNN
• Modelling sequences
• Training RNNs with Backpropagation
• Long Short-Term memory (LSTM)
• Recursive Neural Tensor Network Theory
• Recurrent Neural Network Model

Hands-On

• Building a recurrent neural network for SPAM prediction.

 Restricted Boltzmann Machine (RBM) and Autoencoders

Learning Objectives: In this module, you’ll understand RBM & Autoencoders along with their applications. You will understand the working of RBM & Autoencoders, illustrate Collaborative Filtering using RBM and understand what are Deep Belief Networks.

 Topics:

• Restricted Boltzmann Machine
• Applications of RBM
• Collaborative Filtering with RBM
• Introduction to Autoencoders
• Autoencoders applications
• Understanding Autoencoders

Hands-On

• Building a Autoencoder model for classification of handwritten images extracted from the MNIST Dataset

 Keras API

Learning Objectives:

 In this module, you’ll understand how to use Keras API for implementing Neural Networks. The goal is to understand various functions and features that Keras provides to make the task of neural network implementation easy.

 Topics:

• Define Keras
• How to compose Models in Keras
• Sequential Composition
• Functional Composition
• Predefined Neural Network Layers
• What is Batch Normalization
• Saving and Loading a model with Keras
• Customizing the Training Process
• Using TensorBoard with Keras
• Use-Case Implementation with Keras

Hands-On

• Build a model using Keras to do sentiment analysis on twitter data reactions on GOP debate in Ohio

 TFLearn API

Learning Objectives:In this module, you’ll understand how to use TFLearn API for implementing Neural Networks. The goal is to understand various functions and features that TFLearn provides to make the task of neural network implementation easy.

 Topics:

• Define TFLearn
• Composing Models in TFLearn
• Sequential Composition
• Functional Composition
• Predefined Neural Network Layers
• What is Batch Normalization
• Saving and Loading a model with TFLearn
• Customizing the Training Process
• Using TensorBoard with TFLearn
• Use-Case Implementation with TFLearn

Hands-On

• Build a recurrent neural network using TFLearn to do image classification on hand-written digits

 In-Class Project

Learning Objectives:In this module, you should learn how to approach and implement a project end to end. The instructor will share his industry experience and related insights that will help you kickstart your career in this domain. In addition, we will be having a QA and doubt clearing session for you.

 Topics:

• How to approach a project? 
• Hands-On project implementation
• What Industry expects?
• Industry insights for the Machine Learning domain
• QA and Doubt Clearing Session

 Introduction to Big Data Hadoop and Spark

Learning Objectives: In this module, you will understand Big Data, the limitations of the existing solutions for Big Data problem, how Hadoop solves the Big Data problem, Hadoop ecosystem components, Hadoop Architecture, HDFS, Rack Awareness, and Replication. You will learn about the Hadoop Cluster Architecture, important configuration files in a Hadoop Cluster. You will also get an introduction to Spark, why it is used and understanding of the difference between batch processing and real-time processing. 

 Topics:

• What is Big Data?
• Big Data Customer Scenarios
• Limitations and Solutions of Existing Data Analytics Architecture with Uber Use Case
• How Hadoop Solves the Big Data Problem?
• What is Hadoop?
• Hadoop’s Key Characteristics
• Hadoop Ecosystem and HDFS
• Hadoop Core Components
• Rack Awareness and Block Replication
• YARN and its Advantage
• Hadoop Cluster and its Architecture
• Hadoop: Different Cluster Modes
• Big Data Analytics with Batch & Real-Time Processing
• Why Spark is Needed?
• What is Spark?
• How Spark Differs from its Competitors?
• Spark at eBay
• Spark’s Place in Hadoop Ecosystem

 Introduction to Python for Apache Spark

Learning Objectives: In this module, you will learn basics of Python programming and learn different types of sequence structures, related operations and their usage. You will also learn diverse ways of opening, reading, and writing to files. 

 Topics:

• Overview of Python
• Different Applications where Python is Used
• Values, Types, Variables
• Operands and Expressions
• Conditional Statements
• Loops
• Command Line Arguments
• Writing to the Screen
• Python files I/O Functions
• Numbers
• Strings and related operations
• Tuples and related operations
• Lists and related operations
• Dictionaries and related operations
• Sets and related operations

 Hands-On:

• Creating “Hello World” code
• Demonstrating Conditional Statements
• Demonstrating Loops
• Tuple - properties, related operations, compared with list
• List - properties, related operations
• Dictionary - properties, related operations
• Set - properties, related operations

 Functions, OOPs, and Modules in Python

Learning Objectives: In this Module, you will learn how to create generic python scripts, how to address errors/exceptions in code and finally how to extract/filter content using regex. 

 Topics:

• Functions
• Function Parameters
• Global Variables
• Variable Scope and Returning Values
• Lambda Functions
• Object-Oriented Concepts
• Standard Libraries
• Modules Used in Python
• The Import Statements
• Module Search Path
• Package Installation Ways

 Hands-On:

• Functions - Syntax, Arguments, Keyword Arguments, Return Values
• Lambda - Features, Syntax, Options, Compared with the Functions
• Sorting - Sequences, Dictionaries, Limitations of Sorting
• Errors and Exceptions - Types of Issues, Remediation
• Packages and Module - Modules, Import Options, sys Path

 Deep Dive into Apache Spark Framework

Learning Objectives: In this module, you will understand Apache Spark in depth and you will be learning about various Spark components, you will be creating and running various spark applications. At the end, you will learn how to perform data ingestion using Sqoop. 

 Topics:

• Spark Components & its Architecture
• Spark Deployment Modes
• Introduction to PySpark Shell
• Submitting PySpark Job
• Spark Web UI
• Writing your first PySpark Job Using Jupyter Notebook
• Data Ingestion using Sqoop

 Hands-On:

• Building and Running Spark Application
• Spark Application Web UI
• Understanding different Spark Properties

 Playing with Spark RDDs

Learning Objectives: In this module, you will learn about Spark - RDDs and other RDD related manipulations for implementing business logics (Transformations, Actions, and Functions performed on RDD). 

 Topics:

• Challenges in Existing Computing Methods
• Probable Solution & How RDD Solves the Problem
• What is RDD, It’s Operations, Transformations & Actions
• Data Loading and Saving Through RDDs
• Key-Value Pair RDDs
• Other Pair RDDs, Two Pair RDDs
• RDD Lineage
• RDD Persistence
• WordCount Program Using RDD Concepts
• RDD Partitioning & How it Helps Achieve Parallelization
• Passing Functions to Spark

 Hands-On:

• Loading data in RDDs
• Saving data through RDDs
• RDD Transformations
• RDD Actions and Functions
• RDD Partitions
• WordCount through RDDs

 DataFrames and Spark SQL

Learning Objectives: In this module, you will learn about SparkSQL which is used to process structured data with SQL queries. You will learn about data-frames and datasets in Spark SQL along with different kind of SQL operations performed on the data-frames. You will also learn about the Spark and Hive integration. 

 Topics:

• Need for Spark SQL
• What is Spark SQL
• Spark SQL Architecture
• SQL Context in Spark SQL
• Schema RDDs
• User Defined Functions
• Data Frames & Datasets
• Interoperating with RDDs
• JSON and Parquet File Formats
• Loading Data through Different Sources
• Spark-Hive Integration

 Hands-On:

• Spark SQL – Creating data frames
• Loading and transforming data through different sources
• Stock Market Analysis
• Spark-Hive Integration

 Machine Learning using Spark MLlib

Learning Objectives: In this module, you will learn about why machine learning is needed, different Machine Learning techniques/algorithms and their implementation using Spark MLlib.

 Topics:

• Why Machine Learning
• What is Machine Learning
• Where Machine Learning is used
• Face Detection: USE CASE
• Different Types of Machine Learning Techniques
• Introduction to MLlib
• Features of MLlib and MLlib Tools
• Various ML algorithms supported by MLlib

 Deep Dive into Spark MLlib

Learning Objectives: In this module, you will be implementing various algorithms supported by MLlib such as Linear Regression, Decision Tree, Random Forest and many more. 

 Topics:

• Supervised Learning: Linear Regression, Logistic Regression, Decision Tree, Random Forest
• Unsupervised Learning: K-Means Clustering & How It Works with MLlib
• Analysis of US Election Data using MLlib (K-Means)

 Hands-On:

• K- Means Clustering
• Linear Regression
• Logistic Regression
• Decision Tree
• Random Forest

 Understanding Apache Kafka and Apache Flume

Learning Objectives: In this module, you will understand Kafka and Kafka Architecture. Afterwards you will go through the details of Kafka Cluster and you will also learn how to configure different types of Kafka Cluster. After that you will see how messages are produced and consumed using Kafka API’s in Java. You will also get an introduction to Apache Flume, its basic architecture and how it is integrated with Apache Kafka for event processing. You will learn how to ingest streaming data using flume. 

 Topics:

• Need for Kafka
• What is Kafka
• Core Concepts of Kafka
• Kafka Architecture
• Where is Kafka Used
• Understanding the Components of Kafka Cluster
• Configuring Kafka Cluster
• Kafka Producer and Consumer Java API
• Need of Apache Flume
• What is Apache Flume
• Basic Flume Architecture
• Flume Sources
• Flume Sinks
• Flume Channels
• Flume Configuration
• Integrating Apache Flume and Apache Kafka

Hands-On:

• Configuring Single Node Single Broker Cluster
• Configuring Single Node Multi-Broker Cluster
• Producing and consuming messages through Kafka Java API
• Flume Commands
• Setting up Flume Agent
• Streaming Twitter Data into HDFS

 Apache Spark Streaming - Processing Multiple Batches

Learning Objectives: In this module, you will work on Spark streaming which is used to build scalable fault-tolerant streaming applications. You will learn about DStreams and various Transformations performed on the streaming data. You will get to know about commonly used streaming operators such as Sliding Window Operators and Stateful Operators. 

 Topics:

• Drawbacks in Existing Computing Methods
• Why Streaming is Necessary
• What is Spark Streaming
• Spark Streaming Features
• Spark Streaming Workflow
• How Uber Uses Streaming Data
• Streaming Context & DStreams
• Transformations on DStreams
• Describe Windowed Operators and Why it is Useful
• Important Windowed Operators
• Slice, Window and ReduceByWindow Operators
• Stateful Operators

 Hands-On:

• WordCount Program using Spark Streaming

 Apache Spark Streaming - Data Sources

Learning Objectives: In this module, you will learn about the different streaming data sources such as Kafka and flume. At the end of the module, you will be able to create a spark streaming application. 

 Topics:

• Apache Spark Streaming: Data Sources
• Streaming Data Source Overview
• Apache Flume and Apache Kafka Data Sources
• Example: Using a Kafka Direct Data Source

 Hands-On:

• Various Spark Streaming Data Sources

 Implementing an End-to-End Project

Project 1-

•  Domain: Finance

Statement:

•  A leading financial bank is trying to broaden the financial inclusion for the unbanked population by providing a positive and safe borrowing experience. In order to make sure this underserved population has a positive loan experience, it makes use of a variety of alternative data--including telco and transactional information--to predict their clients` repayment abilities. The bank has asked you to develop a solution to ensure that clients capable of repayment are not rejected and that loans are given with a principal, maturity, and repayment calendar that will empower their clients to be successful.

Project 2-

•  Domain: Media and Entertainment 

Statement:

•  Analyze and deduce the best performing movies based on the customer feedback and review. Use two different API`s (Spark RDD and Spark DataFrame) on datasets to find the best ranking movies.

 Spark GraphX (Self-Paced)

Learning Objective: In this module, you will be learning the key concepts of Spark GraphX programming concepts and operations along with different GraphX algorithms and their implementations. 

 Topics:

• Introduction to Spark GraphX
• Information about a Graph
• GraphX Basic APIs and Operations
• Spark GraphX Algorithm - PageRank, Personalized PageRank, Triangle Count, Shortest Paths, Connected Components, Strongly Connected Components, Label Propagation

 Hands-On:

• The Traveling Salesman problem
• Minimum Spanning Trees