Machine Learning

Overview:

This module provides an overview of machine learning, its concepts, applications, and significance in data-driven decision-making.

Topics to Cover:

• Machine Learning Intuitions
• Machine Learning Workflow
• Train 1st model

Overview:

This module explores the KNN algorithm, its implementation, and its applications in classification tasks.

Topics to Cover:

• Understand the concept of KNN
• Implement KNN using Python
• Implement KNN with Numpy

Overview:

This modules examines the principles of linear regression and its use in predicting continuous outcomes.

Topics to Cover:

• Understand the concept of Linear Regression
• Understand the calculation of the model
• Work with single and multiple Linear Regression
• Evaluation of the model

Overview:

This module dives into various classification techniques, focusing on logistic regression for binary classification problems.

Topics to Cover:

• Classification vs. Regression
• What is Logistic Regression
• Learn about decision boundaries
• Using single and multiple Logistic Regressions
• Evaluate Logistic Regressions

Overview:

This module examines EDA techniques to analyze data, identify patterns, and inform modeling strategies.

Topics to Cover:

• What is EDA?
• What are done in EDA?
• Understand the datasets

Overview:

This module focuses on the importance of data cleaning and preprocessing techniques for preparing data for analysis.

Topics to Cover:

• What is Data Preprocessing?
• Creating a ML Dataset
• Split and Scale Data
• Dealing with imbalanced dataset
• Transform columns
• Clean dataset

Overview:

This module explores feature engineering methods to enhance model performance through the creation and selection of relevant features.

Topics to Cover:

• What is Feature Engineering?
• Common ways to automatically create features
• Dealing with missing values or outliers
• Working with Text Features

Overview:

This module shows dimension reduction methods, such as PCA, to simplify datasets while retaining essential information.

Topics to Cover:

• What is PCA?
• Importance of Feature Selection
• Impact of Dimension Reduction

Overview:

This module focuses on decision trees, their structure, and their applications in classification and regression tasks.

Topics to Cover:

• Implement Decision Trees
• Understand the decision boundaries
• Creating Decision Trees from scratch
• Classification vs Regression Trees

Overview:

This module demonstrates techniques for model validation, performance evaluation, and parameter tuning for optimal results.

Topics to Cover:

• Model Validation methods
• Tune parameters
• Using cross validation

Overview:

This module explores ensemble methods, including bagging and boosting, and their applications in improving model accuracy.

Topics to Cover:

• Random Forest, Bagging, and Boosting methods
• Examine various boosting methods such as Gradient Boosting, XGBoost, LightGBM and CatBoost

Overview:

This module teaches the importance of model interpretation and techniques for achieving explainable AI.

Topics to Cover:

• How to interpret models
• Using LIME and SHAP
• Examine feature importance

Overview:

This module shows insights into unsupervised learning techniques, including clustering and association rule learning.

Topics to Cover:

• Using k-Means clustering
• Learn about hierarchical clustering
• Dimension reduction using t-SNE and UMAP

Overview:

This module explores the fundamentals of neural networks and deep learning, including architectures and applications.

Topics to Cover:

• Understand the mathematics behind NN calculation
• Creating simple NN from scratch
• Working with NN using PyTorch

Overview:

This module shows how to build recommender systems using collaborative filtering and content-based methods.

Topics to Cover:

• What is Recommender System?
• Collaborative Filtering vs Content-Based Filtering

Overview:

This module demonstrates the basics of NLP and its applications in processing and analyzing textual data.

Topics to Cover:

• What is NLP?
• Basic Text Preprocessing techniques
• Applying TF-IDF
• Application: Topic Modelling

Overview:

This modules demonstrates the basics of ML Operations.

Topics to Cover:

• Putting together a pipeline
• Deploy model using Flask
• Intro into SageMaker

Overview:

This module applies ML models using real-world use cases.

Topics to Cover:

• Apply ML Models in different industries
• Use real-life datasets to practice skills