INTRODUCTION TO DATA SCIENCE DEEP LEARNING &

ARTIFICIALINTELLIGENCE

Introduction to Deep Learning & AI

Deep Learning: A revolution in Artificial Intelligence

 Limitations of Machine Learning

What is Deep Learning?

 Need for Data Scientists

 Foundation of Data Science

 What is Business Intelligence

 What is Data Analysis

 What is Data Mining

What is Machine

Learning? Analytics

vs. Data Science

 Value Chain

 Types of Analytics

 Lifecycle Probability

 Analytics Project Lifecycle

 Advantage of Deep Learning over Machine learning

 Reasons for Deep Learning

 Real-Life use cases of Deep Learning

 Review of Machine Learning

 Basis of Data Categorization

 Types of Data

 Data Collection Types

 Forms of Data & Sources

 Data Quality & Changes

 Data Quality Issues

 Data Quality Story

 What is Data Architecture

 Components of Data Architecture

 OLTP vs. OLAP

 How is Data Stored?

Big Data

 What is Big Data?

 5 Vs of Big Data

 Big Data Architecture

 Big Data Technologies

 Big Data Challenge

 Big Data Requirements

 Big Data Distributed Computing & Complexity

 Hadoop

 Map Reduce Framework

 Hadoop Ecosystem
Data Science Deep Dive

 What Data Science is

 Why Data Scientists are in demand

 What is a Data Product

 The growing need for Data Science

 Large Scale Analysis Cost vs Storage

 Data Science Skills

 Data Science Use Cases

 Data Science Project Life Cycle & Stages

 Data Acquisition

 Where to source data

 Techniques

 Evaluating input data

 Data formats

 Data Quantity

 Data Quality

 Resolution Techniques

 Data Transformation

 File format Conversions

 Annonymization
 PYTHON

 Python Overview

 About Interpreted Languages

 Advantages/Disadvantages of Python pydoc.

 Starting Python

 Interpreter PATH

 Using the Interpreter

 Running a Python Script

 Using Variables

 Keywords

 Built-in Functions

 Strings Different Literals

 Math Operators and Expressions

 Writing to the Screen

 String Formatting

 Command Line Parameters and Flow Control.

 Lists

 Tuples

 Indexing and Slicing

 Iterating through a Sequence

 Functions for all Sequences

 The xrange() function

 List Comprehensions

 Generator Expressions

 Dictionaries and Sets.

Numpy & Pandas

 Learning NumPy

 Introduction to Pandas

 Creating Data Frames

 Grouping Sorting

 Plotting Data

 Creating Functions

 Slicing/Dicing Operations.
Deep Dive – Functions & Classes & Oops

 Functions

 Function Parameters

 Global Variables

 Variable Scope and Returning Values. Sorting

 Alternate Keys

 Lambda Functions

 Sorting Collections of Collections

 Classes & OOPs

STATISTICS

 What is Statistics

 Descriptive Statistics

 Central Tendency Measures

 The Story of Average

 Dispersion Measures

 Data Distributions
 Central Limit Theorem

 What is Sampling

 Why Sampling

 Sampling Methods

 Inferential Statistics

 What is Hypothesis testing

 Confidence Level

 Degrees of freedom

 what is pValue

 Chi-Square test

 What is ANOVA

 Correlation vs Regression

 Uses of Correlation & Regression

Introduction

 ML Fundamentals

 ML Common Use Cases

 Understanding Supervised and Unsupervised Learning Techniques

Clustering

 Similarity Metrics

 Distance Measure Types: Euclidean, Cosine Measures

 Creating predictive models

 Understanding K-Means Clustering

 Understanding TF-IDF, Cosine Similarity and their application to Vector Space

Model

 Case study

Implementing Association rule mining

 What is Association Rules & its use cases?

 What is Recommendation Engine & it’s working?

 Recommendation Use-case

 Case study
 Understanding Process flow of Supervised

Learning Techniques Decision Tree Classifier

 How to build Decision trees

 What is Classification and its use cases?

 What is Decision Tree?

 Algorithm for Decision Tree Induction

 Creating a Decision Tree

 Confusion Matrix

 Case stud

Random Forest Classifier

 What is Random Forests

 Features of Random Forest

 Out of Box Error Estimate and Variable Importance

 Case study

Naive Bayes Classifier.

 Case study
Project Discussion

Problem Statement and Analysis

 Various approaches to solve a Data Science Problem

 Pros and Cons of different approaches and algorithms.

Linear Regression

 Case study

 Introduction to Predictive Modeling

 Linear Regression Overview

 Simple Linear Regression

 Multiple Linear Regression

Logistic Regression

 Case study

 Logistic Regression Overview

 Data Partitioning

 Univariate Analysis

 Bivariate Analysis

 Multicollinearity Analysis

 Model Building

 Model Validation
  Model Performance Assessment AUC & ROC curves

 Scorecard

Support Vector Machines

 Case Study

 Introduction to SVMs

 SVM History

 Vectors Overview

 Decision Surfaces

 Linear SVMs

 The Kernel Trick

 Non-Linear SVMs

 The Kernel SVM

Time Series Analysis

 Describe Time Series data

 Format your Time Series data

 List the different components of Time Series data

 Discuss different kind of Time Series scenarios

 Choose the model according to the Time series scenario

 Implement the model for forecasting

 Explain working and implementation of ARIMA model

 Illustrate the working and implementation of different ETS models

 Forecast the data using the respective model

 Time Series variables

 Different components of Time Series data

 Visualize the data to identify Time Series Components

 Implement ARIMA model for forecasting

 Exponential smoothing models

 Identifying different time series scenario based on which different Exponential

Smoothing model can be applied

 Implement respective model for forecasting

 Visualizing and formatting Time Series data

 Plotting decomposed Time Series data plot

 Applying ARIMA and ETS model for Time Series forecasting

 Forecasting for given Time period

 Case Study

Machine Learning Project

Machine learning algorithms Python

 Various machine learning algorithms in Python

 Apply machine learning algorithms in Python

 How to select the right data

 Which are the best features to use

 Additional feature selection techniques

 A feature selection case study

 Preprocessing

 Preprocessing Scaling Techniques

 How to preprocess your data

 How to scale your data

 Feature Scaling Final Project

Which Algorithms perform best

 Highly efficient machine learning algorithms

 Bagging Decision Trees

 The power of ensembles

 Random Forest Ensemble technique

 Boosting – Adaboost

 Boosting ensemble stochastic gradient boosting

 A final ensemble technique

 Introduction Model Tuning

 Parameter Tuning GridSearchCV

 A second method to tune your algorithm

 How to automate machine learning

 Which ML algo should you choose

 How to compare machine learning algorithms in practice

Text Mining& NLP

 Sentimental Analysis

 Case study

PySpark and MLLib

 Introduction to Spark Core

 Spark Architecture

 Working with RDDs

 Introduction to PySpark

 Machine learning with PySpark – Mllib

Deep Learning & AI

 Case Study

 Deep Learning Overview

 The Brain vs Neuron

 Introduction to Deep Learning

Introduction to Artificial Neural Networks

 The Detailed ANN

 The Activation Functions

 How do ANNs work & learn

 Gradient Descent

 Stochastic Gradient Descent

 Backpropogation

 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

 Building a multi-layered perceptron for classification

 Why Deep Networks give better accuracy?

 Use-Case Implementation

 Understand How Deep Network Works?

 How Backpropagation Works?

 Illustrate Forward pass, Backward pass

 Different variants of Gradient Descent

Convolutional Neural Networks

 Convolutional Operation

 Relu Layers

 What is Pooling vs Flattening

 Full Connection

 Softmax vs Cross Entropy

 ” Building a real world convolutional neural network

 for image classification”

What are RNNs – Introduction to RNNs

 Recurrent neural networks rnn

 LSTMs understanding LSTMs

 long short term memory neural networks lstm in python

 Restricted Boltzmann Machine

 Applications of RBM

 Introduction to Autoencoders

 Autoencoders applications

 Understanding Autoencoders

 Building a Autoencoder model

Tensorflow with Python

 Introducing Tensorflow

 Introducing Tensorflow

 Why Tensorflow?

 What is tensorflow?

 Tensorflow as an Interface

 Tensorflow as an environment

 Tensors

 Computation Graph

 Installing Tensorflow

 Tensorflow training

 Prepare Data

 Tensor types

 Loss and Optimization

 Running ensorflow programs

Tensorflow

 Tensors

 Tensorflow data types

 CPU vs GPU vs TPU

 Tensorflow methods

 Introduction to Neural Networks

 Neural Network Architecture

 Linear Regression example revisited

 The Neuron

 Neural Network Layers

 The MNIST Dataset

 Coding NIST NN

Deep Learning using Tensorflow

 Deepening the network

 Images and Pixels

 How humans recognise images

 Convolutional Neural Networks

 ConvNet Architecture

 Overfitting and Regularization

 Max Pooling and ReLU activations

 Dropout

 Strides and Zero Padding

 Coding Deep ConvNets demo

 Visualising NN using Tensorflow

 Tensorboard

Transfer Learning using Keras and TFLearn

 Transfer Learning Introduction

 Google Inception Model

 Retraining Google Inception with our own data demo

 Predicting new images

 Transfer Learning Summary

 Extending Tensorflow

 Keras

 TFLearn

 Keras vs TFLearn Comparison

Start Data Science Course Online