EDDZE - Python for Machine Learning

20%

Course Description

Data Science, Machine Learning, Deep Learning and Artificial Intelligence

Objectives of the Program

To enable participants understand how Data Science is used in every aspect of our daily lives and businesses
To enable the participants to learn basics of Python.
To enable the participants to learn Data Science/Machine learning/Deep Learning using Python.
To empower the participants with sufficient knowledge to use latest technologies of Data Science (Hands-On).
To make the participants understand overview of how Exploratory Data Analysis works.
To provide the participants Hands-on experience in Data science concepts.
To provide the participants Hands-on experience in Machine Learning concepts.
To empower the participants with sufficient knowledge to use latest technologies of Data Science/Machine Learning/Deep Learning/ Artificial Intelligence (Hands-On).
Overview of the Program Content
Introduction to Data Science, Machine Learning, Deep Learning and Artificial Intelligence
Basics of Python and Hands-on on Python
Introduction to Data Science using Python
Hands on session on Data Science with Python [Database Connectivity with PYTHON: Performing Database Transactions (Inserting, Deleting, and Updating the Database)]
Introduction to Machine Learning and its types
Examples Overview of Machine Learning packages in Python
Introduction to Deep Learning and its types
Project in Data Science/Machine Learning /Artificial Intelligence

CURRICULUM DETAILS: MODULES AND CHAPTERS

Module 1: Python for Data Science/Machine Learning/Deep Learning

Basic building blocks of python
Data Types
Operators
Control Structure
Functions
Data Structures
String Operations and Regular Expressions
File Handling
Exception Handling
The Object-Oriented Approach

Module 2: Maths Behind Data Science

Statistical Analysis: Descriptive Statistics & Inferential Statistics
Hypothesis Testing

Module 3: Data Science (Exploratory data analysis (EDA) /Data wrangling/
Data Munging/Data Cleaning Techniques/ Data Preparation/Feature
Engineering)

o Data Science Library and data visualization Using Python
o Data Exploration (Univariate/Bivariate/Multivariate Analysis)
o Missing value treatment
o Outlier treatment
o Categorical to Numerical
o Feature Rescaling
o Feature (Variable) transformations
o Correlation Analysis
o Feature selection Methods

Module 4: Data Visualization using Tableau

Module 5: Introduction to Machine Learning: Supervised Learning

Regression Analysis- Simple Linear Regression, Multiple Linear Regression, Polynomial Regression, Advanced Regression
Classification Methods- Logistic Regression/Naïve Bayes/KNN/ Support Vector Machines (SVM)/Decision Tree/Random Forest

Module 6: Supervised Learning: Classification Methods: Ensemble

Techniques

Bootstrap Aggregation (Bagging) Ensemble Learning
Boosting Ensemble Learning

Module 7: Unsupervised Machine Learning

Clustering Techniques
Dimensionality Reductionality

Module 8: Model Tuning, Model Selection and Hyperparameters

Cross Validation Techniques
Model selection and Tuning
Model Performance and Measure (Evaluation Metrics)
Model Regularization Method
Imbalance data Treatment
Model Hyperparameter optimization
ML Pipeline

Module 9: Introduction to Neural network for Deep Learning

Introduction to Tensorflow/Keras/Pytorch
Biological Neuron/ Artificial Neuron (Perceptron)
Perceptron/MLP/ Vanilla Neural Network/ANN
Types of ANN: Sequential ANN and Functional ANN
Weight Initialization and Biases
Activation Functions
Backward Propogation
Gradient Descent
Learning rate
Optimizers
Regularization
Loss Function and Cost Function
Hyperparameters

Module 10: Computer vision

Introduction to computer Vision and Image Processing
Introduction to CNN
Introduction to CNN Architectures and Transfer Learning
Image Classification using CNN and Transfer Learning

Module 11: Advanced Computer Vision

Object Detection
Image Segmentation
Semantic Segmentation

Module 12: Natural Language Processing (NLP) Basics

Introduction to NLP
Text Preprocessing
Bag of words Model and TF-IDF
Introduction to Language Model: N-grams/Word2vec/Glove

Module 13: Sequential Models and NLP

Introduction Recurrent Neural Network (RNN)
Introduction to Long Short term Memory (LSTM)
Introduction to GRU
Introduction to Encoder –Decoder
Introduction to Transformer
Introduction to BERT
Introduction to GPT3

Module 14: Unsupervised Deep Learning
o Introduction to GAN and its types
o Introduction to Autoencoder

List of Projects for Internship/Final Year Projects
1. EDA in Covid-19 Live Tracking Analysis from Government Website
2. Cancer Prediction using Machine Learning
3. Machine Learning for Classification of Fraudulent and Non-Fraudulent Transactions
4. Credit Card Fraud Detection Project
5. Customer Segmentation
6. Customer Churn Prediction
7. Recommendation System
8. Housing Prices Prediction Project
9. Movies Award Prediction
10. MNIST Handwritten Digit Image Classification using Artificial Neural Network (ANN)
11. MNIST Handwritten Digit Image Classification using Convolution Neural Network (CNN)
12. Bean Leaf Disease Image Classification
13. Human vs Horse Image Classification
14. Cat Vs Dog Image Classification
15. Chatbots
16. Sentiment Analysis
17. Image to Image Generation
18. Denoising of Images using Autoencoder
19. GAN
20. Image super resolution using GAN