• Artificial Intelligence & Machine Learning Introduction
• Who uses AI?
• Area of Artificial Intelligence
• AI v/s ML v/s DL and Data Science
• Typical applications of Machine Learning for optimizing IT Operations

• Types of variable
• Categorical and Continuous Data
• Ratio and Interval
• Nominal and Ordinal Data
• Measure of Central Tendency – Mean, Mode and Median
• Percentile and Quartile
• Measure of Spread – IQR, Variance and Standard Deviation
• Empirical Rule
• Chebyshev’s Theorem
• Z Test
• Coefficient of Variation
• Kurtosis and Skewness

Analyzing Categorical and Continuous Data

• Proportional Test
• Chi Square Test
• Covariance
• Correlation
• T Test
• Anova

Probabilistic Analysis

• Events and their Probabilities
• Rules of Probability
• Conditional Probability and Independence
• Bayes Theorem
• Moment Generating Functions Central
• Limit Theorem
• Expectation & Variance
• Standard Distributions – Bernoulli, Binomial & Multinomial

• Getting started with Python
• What is Python?
• Installing Anaconda
• Variables, and Data Structure
• List, tuples and dictionary
• Control Structure
• Functions in python
• Lambda functions
• Object Oriented Programming
• Modules
• Using Packages
• Os package
• time and datetime
• File Handling in Python
• Miscellaneous Functions in python 

• Introduction to Statistics
• Population and Sample  
• Descriptive Statistics v/s Inferential Statistics
• Types of variable
• Categorical and Continuous Data
• Ratio and Interval
• Nominal and Ordinal Data

Descriptive Statistics

• Measure of Central Tendency – Mean, Mode and Median
• Percentile and Quartile
• Measure of Spread – IQR, Variance and Standard Deviation
• Coefficient of Variation
• Measure of Shape – Kurtosis and Skewness
• Correlation Analysis

Inferential Statistics

• Empirical Rule & Chebyshev’s Theorem
• Z Test
•  One Sample T test, independent t test
• ANOVA – f test
• Chi Square test

Working with Numpy

• NumPy Overview
• Properties, Purpose, and Types of ndarray
• Class and Attributes of ndarray Object
• Basic Operations: Concept and Examples
• Accessing Array
• Elements: Indexing, Slicing, Iteration, Indexing with Boolean Arrays
• Shape Manipulation & Broadcasting
• Linear Algebra using numpy
• Stacking and resizing the array
• random numbers using numpy

Working with Pandas

• Data Structures
• Series, DataFrame & Panel
• DataFrame basic properties
• Importing excel sheets, csv files, executing sql queries
• Importing and exporting json files
• Data Selection and Filtering
• Selection of columns and rows
• Filtering Dataframes
• Filtering – AND operaton and OR operation

Working with Pandas

• Data Cleaning
• Handling Duplicates
• Handling unusual values
• handling missing values
• Finding unique values
• Descriptive Analysis with pandas
• Creating new features
• Creating new categorical features from continuous variable
• combining multiple dataframes
• groupby operations
• groupby statistical Analysis
• Apply method
• String Manipulation 

Basic Visualization with matplotlib

• Matplotlib Features
• Line Properties
• Plot with (x, y)
• Controlling Line Patterns and Colors
• Set Axis, Labels, and Legend Properties
• Alpha and Annotation
• Multiple PlotsSubplots
• Advance visualization using seaborn
• Types of Plots and Seaborn
• Boxplots
• Distribution Plots
• Countplots
• Heatmaps
• Voilin plots
• Swarmplots and pointplots

• The conceptual idea of linear regression
• Predictive Equation
• Cost function formation
• Gradient Descent Algorithm
• OLS approach for Linear Regression
• Multivariate Regression Model
• Correlation Analysis – Analyzing the dependence of variables
• Apply Data Transformations
• Overfitting 
• L1 & L2 Regularization
• Identify Multicollinearity in Data Treatment on Data
• Identify Heteroscedasticity Modelling of Data
• Variable Significance Identification
• Model Significance Test
• R2, MAPE, RMSE
• Project: Predictive Analysis using Linear Regression 

• Classification Problem Analysis
• Variable and Model Significance
• Sigmoid Function
• Cost Function Formation
• Mathematical Modelling 
• Model Parameter Significance Evaluation
• implementing logistic regression using sklearn
• Performance analysis for classification problem
• Confusion Matrix Analysis
• Accuracy, recall, precision and F1 Score
• Specificity and Sensitivity
• Drawing the ROC Curve
• AUC for ROC 
• Classification Report Analysis
• Estimating the Classification Model
•  

K Nearest Neighbour

• Understanding the KNN
• Distance metrics
• KNN for Regression & classification
• implementing KNN using Python
• Case Study on KNN
• handling overfitting and underfitting with KNN

Decision Tree

• Forming Decision Tree
• Components of Decision Tree
• Mathematics of Decision Tree
• Entropy Approach
• Gini Entropy Approach
• Variance – Decision Tree for Regression
• Decision Tree Evaluation
• Overfitting of Decision Tree
• Handling overfitting using hyperparameters
• Hyperparameters tuning using gridsearch
• Visualizing Decision Tree using graphviz

• Practical Examples & Case Study

• Bag of Trees
• Random Forest Mathematics
• Examples & use cases using Random Forests

• Neurons, ANN & Working
• Single Layer Perceptron Model
• Multilayer Neural Network
• Feed Forward Neural Network
• Cost Function Formation
• Applying Gradient Descent Algorithm
• Backpropagation Algorithm & Mathematical Modelling
• Programming Flow for backpropagation algorithm
• Use Cases of ANN
• Programming SLNN using Python
• Programming MLNN using Python
• Case study and Assignment

Support Vector Machines

• Concept and Working Principle
• Mathematical Modelling
• Optimization Function Formation
• Slack Variable
• The Kernel Method and Nonlinear Hyperplanes
• Use Cases
• Programming SVM using Python
• Project – Character recognition using SVM

Ensemble Learning

• Concept of Ensemble Learning 
• Bagging and Boosting
• Bagging – Random Forest
• Random Forest for Classification
• Random Forest for Regression
• Boosting – Gradient Boosting Trees
• Boosting – Adaboost
• Boosting – XGBoost
• Stacking
• Case study and assignment

• Image Processing with Opencv
• Image Acquisition and manipulation using opencv
• Video Processing
• Edge Detection
• Corner Detection
• Face Detection
• Image Scaling for ANN
• Face Detection in an image frame
• Object detection
• Training ANN with Images
• Character Recognition
• Case Study and Assignments

• Definition of Time Series
• Time Series Decomposition
• Simple Moving Average Method
• Weighted Moving Average Method
• Single Exponential Smoothing Method
• Double Exponential Smoothing Method
• Triple Exponential Smoothing Method
• Stationarity of Data
• ARIMA Models

Clustering 

• Application of clustering
• Hierarchical Clustering
• K Means Clustering
• Use Cases for K Means Clustering
• Programming for K Means using Python
• Customer segmentation using KMeans
• Cluster Size Optimization vs Definition Optimization

Dimensionality Reduction – PCA

• Dimensionality Reduction, Data Compression
• Curse of dimensionality
• Multicollinearity
• Factor Analysis
• Concept and Mathematical modelling
• Use Cases
• Programming using Python

Principal Component Analysis

• Dimensionality Reduction, Data Compression
• Curse of dimensionality
• Multicollinearity
• Factor Analysis
• Concept and Mathematical modelling
• Use Cases
• Programming using Python

Anomaly Detection

• Moving Average Filtering
• Mean, Standard Deviation
• Statistical approach for Anomaly Detection
• OneClass SVM for Anomaly Detection
• Isolation Forest for Anomaly Detection
• Hands on project on Anomaly Detection
• Do’s and Don’ts for Anomaly Detection

• Natural Language Processing & Generation
• Semantic Analysis and Syntactic Analysis
• Text Cleaning and Preprocessing using Regex
• Using NLTK & Textblob
• Basic Text data processing
• Tokenization, Stemming and Lemmatization
• Pos Tagging
• Tf-IDF, count vector and Word2vec
• Sentiment Analysis
• Using Google, Bing and IBM Speech to Text APIs
• Project: Streaming live tweets and Sentiment Analysis
• Wordcloud

Project: Building an Email Classification Model

Chatbots

1. Building Chatbots using Dialog Flow and Facebook Messenger
2. Facebook Messenger API Integration

• Introduction to Recommendation System
• Popularity based Filtering
• Content based Filtering
• Collaborative Filtering
• Examples and Use cases
• Project: Movie Recommendation System

• Introduction to TensorFlow & Theano
• The Programming Model
• Data Model, Tensor Board
• Working with constants, variables and placeholders
• Linear Regression using Tensorflow
• Logistic Regression using Tensorflow
• Tensorflow low level APIs
• Data manipulation using Tensorflow
• Working with Theano
• Building Linear Regression and Logistic Regression with Theano
• Examples and use cases

• Activation Functions for Neural Networks
• Optimization Techniques – SGD, ADAM, LBFGS
• Regularization
• Momentum in Neural Networks
• Neural Network Tuning and Performance Optimization
• Introducing Feed Forward Neural Nets
• Softmax Classifier & ReLU Classifier
• Dropout Optimization
• Back propagation Neural networks with Tensorlfow
• Deep Neural Networks using Tensorflow

• Gradient Boosting Methods
• GBM – idea and beefits
• XGBoost
• LightGBM
• CatBoost

• Convolutional Neural Networks
• CNN Architecture
• Convolution Process
• MaxPooling, dropout
• Maths behind CNNs
• Feature Extraction
• Variants of the Basic Convolution Function
• Efficient Convolution Algorithms
• The Neuroscientific Basis for Convolutional Networks
• Variety of Convolutional Networks
• Implementing CNNs using Keras
• MNIST Data – Digit Classification using CNN

• Recurrent Neural Networks
• Basic concepts of RNN
• Unfolding Recurrent Neural Networks
• The Vanishing Gradient Problem
• The Exploding Gradient Problem
• LSTM Networks
• Recursive Neural Networks
• Case study
• Basic Time Series Forecasting using LSTM
• Bitcoin Prices prediction using LSTM
• Airlines Volume Prediction using LSTM
• LSTM for NLP
• Word Embedding and LSTM
• Text Classification using LSTM
• Project: IMDB Feedback classification
• Word2vec
• Word Embedding
• Text Classification using LSTM
• Text Summarization using LSTMs
• Concept and methods
• Sequence to Sequence Model using LSTMs
• Assignment
• Autoencoders, RBM
• Introducing Autoencoders
• Representational Power,
• Layer Size and Depth
• Stochastic Encoders and Decoders
• Improving Autoencoders
• Case study
• Restricted Boltzmann Machines
• Math behind RBM
• Concept of Boltzman Machine
• Programming RBM
• Self-Organizing Maps
• Example and Use cases
• Programming SOMs using Keras

Project Work

• Do’s and Don’ts with Machine Learning
• Default Baseline Models
• Determining Whether to Gather More Data
• Selecting Hyperparameters
• Debugging Strategies
• Large Scale
• Productization of Machine Learning/ Deep Learning Application