DATA SCIENCE (ARTIFICIAL INTELLIGENCE – ML & DL)

SYLLABUS

Module 01 – Data Science, Data Analytics, Artificial Intelligence, ML, & DL

• Introduction
• The Data Science Domain
• Data Science, Data Analytics, and Machine Learning, Deep Learning, AI – Overlaps
• Data Science Demystified
• Data Science and Business Strategy
• Successful Companies Using Data Science
• Travel Industry
• Retail
• E-commerce and Crime Agencies
• Analytical Platforms Across Industries
• Key Takeaways.

Module 02 – Data Science & AI in Different Sectors

• Introduction
• AI & ML for Products or Services
• How Google Uses Artificial Intelligence and Data Science
• How LinkedIn Uses Artificial Intelligence and Data Science
• How Amazon Uses Artificial Intelligence and Data Science
• Netflix: Using Artificial Intelligence and Data Science to Drive Engagement
• Media and Entertainment Industry
• Education Industry
• Healthcare Industry
• Government
• Weather Forecasting
• Key Takeaways

Module 03 – Machine Learning-Introduction

• Introduction of Machine Learning
• Evolution of Machine Learning
• Application of Machine Learning

Module 04 – Probability and Stats

• Central tendency theorem
• Probability
• Bayes Theorem
• Types of distribution

 

Module 05 – Machine Learning-Fundamental

• Difference between Traditional Programming and ML Programming
• Requirements for Machine Learning Practical Implementation
• Required software and tools for Machine Learning implementations
• Setup Anaconda
• Installation of PyCharm or Spyder or Jupyter
• Configure PyCharm/Spyder/Jupyter with Anaconda

Module 06 – Python Programming Foundation for Data Science

• Introduction
• Variables
• Data Types with Python
• Assisted Practice: Data Types in Python
• Keywords and Identifiers
• Expressions
• Basic Operators
• Operators in Python
• Functions
• Search for a Specific Element from a Sorted List
• Create a Banking System Using Functions
• String Operations
• String Operations in Python
• Tuples
• Tuples in Python
• Lists
• Lists in Python
• Sets
• Sets in Python
• Dictionaries
• Dictionary in Python
• Dictionary and its Operations
• Conditions and Branching
• Check the Scores of a Course
• While Loop
• Find Even Digit Numbers
• Fibonacci Series Using While Loop
• For Loop
• Calculate the Number of Letters and Digits
• Create a Pyramid of Stars
• Break and Continue Statements

Module 07 – File handling and Package handling using Python

• Learning Objectives
• File Handling
• File Opening and Closing
• Reading and Writing Files
• Directories in File Handling
• Assisted Practice: File Handling
• Modules and Packages
• Assisted Practice: Package Handling

Module 08 – Mathematical Computing using NumPy

• Learning objectives
• NumPy
• Create and Print Numpy Arrays
• Operations
• Executing Basic Operations in Numpy Array
• Performing Operations Using Numpy Array
• Demonstrate the Use of Copy and Use
• Manipulate the Shape of an Array

Module 09 – Data Manipulation with Pandas

• Learning Objectives
• Introduction to Pandas
• Data Structures
• Create Pandas Series
• DataFrame
• Create Pandas DataFrames
• Missing Values
• Handle Missing Values
• Various Data Operations
• Data Operations in Pandas DataFrame

Module 10 – Data visualization with Python

• Learning objectives
• Data Visualization
• Considerations of Data Visualization
• Factors of Data Visualization
• Python Libraries
• Create Your First Plot Using Matplotlib
• Line Properties
• Create a Line Plot for Football Analytics
• Multiple Plots and Subplots
• Create a Plot with Annotation
• Create Multiple Plots to Analyze the Skills of the Players
• Create Multiple Subplots Using plt.subplots
• Types of plots
• Create a Stacked Histogram
• Create a Scatter Plot of Pretest scores and Posttest Scores
• Create a Pie Chart
• Create a Bar Chart
• Create Box Plots
• Create a Waffle Chart
• Analyzing Variables Individually
• Key Takeaways

Module 11 – Steps of Machine Learning Implementations

• Types of Machine Learning
• Labelled Data and Unlabeled Data
• Concept of Supervised Machine Learning
• Concept of Unsupervised Machine Learning
• Steps of Machine Learning
• Concept of Collecting the historic training Data for ML
• Concept of Preprocess data for Machine Learning
• Concept of Train the ML model
• Concept of Test the ML Algorithm
• Concept of using the ML Algorithm

Module 12 – Data Collection for Machine Learning

• Introduction
• Types of Data collection- Offline Data and Online Data
• Practical implementations of Reading the offline dataset using Numpy
• Practical implementations of Reading the online dataset using Numpy
• Practical implementations of Reading the offline dataset using Pandas
• Practical implementations of Reading the online iris dataset using Pandas

Module 13 – Concept of Supervise & Unsupervised Machine Learning

• Introduction
• Types of Machine Learning
• Labelled Data and Unlabeled Data
• Concept of Supervised Machine Learning
• Concept of Unsupervised Machine Learning
• Regression and Classification
• Linear Regression and Logistic Regression

Module 14 – Data Plotting for Machine Learning

• Introduction
• Concept of Univariate plots
• Univariate Histogram Plots.
• Univariate Density Plots.
• Univariate Box and Whisker Plots.
• Concept of Multivariate plots
• Correlation Matrix Plot
• Scatter Matrix Plot

Module 15 – Practical implementation of Supervised ML Algorithm

• Introduction
• Implementation Foundation of Supervised Machine Learning Algorithms
• Regression and Classification
• Linear Regression and Logistic Regression
• Practical implementations of Supervised ML Algorithms- Linear Regression
• Practical implementations of Supervised ML Algorithms- Logistic Regression
• Concept of Sigmoid Function
• k-NN Algorithm
• Naive Bayes Classifiers
• Decision trees and etc.
• Support vector machines
• Introduction to concepts of forecasting
• Forecasting: ARIMA
• Forecasting: Hotlz Winters
• Dimension Reduction
• Ensemble learning
• Bagging (Random forest)
• Gradient boosting

Module 16 – Practical implementation of Unsupervised Machine Learning

• Introduction
• Concepts and Steps of Unsupervised Machine Learning Algorithm
• Concept of Clustering,
• Practical implementations of Machine Learning Unsupervised Algorithms
• K-Means Clustering.

Module 17 – Prepare Data for ML using Data Transformation Methods

• Introduction
• Need for Data Pre-processing
• Data Transforms Steps
• Types of Data Transformation Methods
• Rescale Data
• Standardize Data
• Normalize Data
• Binarize Data

Module 18 – Feature Selection for Machine Learning

• Introduction
• Feature Selection
• Univariate Feature Selection
• Recursive Feature Elimination
• Principal Component Analysis
• Feature Selection based on Importance

Module 19 – Data Resampling Methods for Evaluation of ML Models

• Introduction
• Evaluate Machine Learning Algorithms
• Split into Train and Test Sets
• K-fold Cross Validation
• Leave One Out Cross Validation
• Repeated Random Test-Train Splits
• What Techniques to Use When

Module 20 – Machine Learning Algorithm Performance Evaluation Metrics

• Introduction
• Algorithm Evaluation Metrics
• Logistic Regression Algorithm Performance Evaluation Metrics
• Classification Accuracy (Default).
• Logarithmic Loss.
• Area Under ROC Curve (AUC).
• Confusion Matrix.
• Classification Report.
• Linear Regression Algorithm Performance Evaluation Metrics
• Mean Absolute Error.
• Mean Squared Error.
• R2 Error

Module 21 – Spot-Check Machine Learning Algorithms

• Concept of Algorithm Spot-Checking
• Algorithms Overview
• Linear Machine Learning Algorithms Spot-check
• Nonlinear Machine Learning Algorithms Spot-check

Module 22 – Save and Load Machine Learning Models

• Introduction
• Finalize Your Model with pickle
• Finalize Your Model with Joblib

Module 23 – Introduction to Deep Learning

• A revolution in Artificial Intelligence
• Limitations of Machine Learning
• What is Deep Learning?
• Advantage of Deep Learning over Machine learning

Module 24 – Introduction to Neural Networks

• How Deep Learning Works?
• Introduction to Neural Networks
• Neural Network Architecture
• The Neuron
• Training a Perceptron
• Concept of Gradient Descent
• Stochastic Gradient Descent (SDG)
• Activation Functions
• Neural Network Layers

Module 25 – Deep dive into ANN with Tensor Flow

• Understand limitations of a Single Perceptron
• Deepening the network
• Tensor Flow code-basics
• Tensor flow data types
• CPU vs GPU vs TPU
• Tensor flow methods
• Overfitting and Regularization
• Debugging Neural Networks
• Visualizing NN using Tensor Flow
• The MNIST Dataset
• Coding MNIST NN
• Linear Regression example revisited
• Generalization, Overfitting, Underfitting

Module 26 – Keras API

• Keras API
• How to compose Models using Keras
• Sequential Composition
• Neural Network Layers with Keras & TensorFlow

Module 27 – Convolutional Neural Networks (CNN)

• Introduction
• Images and Pixels
• How humans recognize images
• Convolutional Neural Networks
• ConvNet Architecture
• Strides and Zero Padding
• Max Pooling and ReLU activations
• Dropout
• Coding Deep ConvNets demo

Module 28 – Computer Vision (CV)

• Introduction to image processing and computer vision
• Convolutional features for visual recognition
• Object detection
• Object tracking and action recognition
• Image segmentation and synthesis

Module 29 – Recurrent Neural Network (RNN)

• Introduction of Recurrent Neural Network
• Architecture of RNN
• Applications of RNN

Module 30 – Natural Language Processing (NLP)

• Introduction of NLP
• Intro to text mining and applications
• Basics of NLP (POS, entity recognition)
• Applications of Regular expression
• Sentiment Analysis
• Topic Modelling
• Clustering in Text documents

Module 31 – Tools for AI

• Introduction to SQL on MySQL
• Introduction to NoSQL on MongoDB
• Introduction to Docker and Kubernetes
• Data lake and centralization strategy
• Using cloud-specific services for AI solution
• Creating and deploying API
• Introduction to ELK Stack
• Introduction to Spark and Distributed Computing

Module 32 – Deployment of AI Solutions

• Unit and System testing
• Model Lifecycle management
• Integration with Dev Ops and relevant architectures
• Retraining Pipeline
• Deployment of AI on Cloud
• AI Ops Best Practices

Module 33 – Mini-Project

• Project Descriptions
• Datasets
• Coding & Implementations
• Performance Evaluation