Applied Machine Learning 

Leveraging AI in Industry

This course equips participants with essential knowledge and practical skills to excel in real-world machine learning applications. The course covers the fundamental concepts of supervised and unsupervised learning, ensemble methods, neural networks, and their applications in diverse industries.

Format

Online Course

Duration

25 Hours

Mode of Delivery

Hybrid Mode

Level

Beginner

Start Date and Time

Nov 2023

Price

₹ 10,000 + GST

*Terms and Conditions Apply.

Target Group

Working professionals looking to advance their knowledge and abilities in AI &ML across a variety of industries and work types.

Target Group

Employees of Participating Organizations who can benefit from the program as part of their professional development initiatives.

Target Group

Recent Graduates who want to acquire additional skills to improve their employability in the field of AI & ML

Target Group

Career Changers looking to transition into a new career field and need to acquire relevant skills in
 AI & ML

Target Group

Entrepreneurs and Small Business Owners who wish to enhance their understanding of AI &ML  for better management and decision-making in their businesses.

Target Group

Unemployed or Underemployed Individuals seeking to upskill in AI &ML to improve their job prospects and career opportunities.

Target Group

People Seeking Career Advancement who are already employed but want to upskill in AI &ML to progress in their current career paths.

Target Group

Learners from non-computer-based backgrounds who are interested in learning AI and ML

 Eligibility Criteria

A basic understanding of machine learning concepts and programming.

Participants should have access to a computer with internet connectivity to engage in the online lectures, exercises, and practical sessions.

Individuals must have a genuine interest in learning AI and Ml.


What is included ?

Interactive Lessons

Engage with interactive lessons that incorporate multimedia elements like videos, quizzes, and exercises to enhance your understanding and retention of the material.

Discussion Forums

Participate in online discussion forums where you can connect with fellow learners, share insights, ask questions, and engage in meaningful discussions related to the course content. .


Write your awesome label here.

Practical Assignments

Participate in practical assignments and projects that reinforce learning, allowing you to apply acquired concepts and skills. Gain hands-on experience and build confidence in the subject matter.

Certificates

Regular assessments and quizzes evaluate your understanding of the course material, track your progress, and provide valuable feedback on your learning journey.

Course Overview

Introduction to
 Machine Learning

Overview of Machine Learning and its applications

Basics of Linear Algebra (vectors, matrices, operations)

Introduction to NumPy for numerical computing in Python

Linear
Regression

Linear Regression: Mathematical formulation

Gradient Descent and optimization

Implementation of Linear Regression using NumPy

Polynomial Regression 

and Regularization

Polynomial Regression: Theory and implementation
Overfitting and Underfitting issues in regression
Regularization methods (L1, L2 regularization)
Regularized Linear Regression with NumPy

 Classification and
 Logistic Regression

Introduction to Classification problems

Logistic Regression: Mathematical foundation and binary classification

Loss Functions for Classification (Cross-Entropy, Hinge Loss)

Implementing Logistic Regression with NumPy

Decision Trees and
Random Forests

Decision Trees: Theory and implementation

Gini Index and Information Gain for splitting

Random Forests: Bagging and Pruning techniques

Building Random Forests from scratch with NumPy

Ensemble Learning 
Boosting and XGBoost

Introduction to Boosting and its advantages

Gradient Boosting: Theory and implementation

Introduction to XGBoost and its features

Implementing Gradient Boosting with XGBoost library

Clustering

Introduction to Unsupervised Learning and Clustering

K-Means Clustering: Algorithm and mathematical details

Determining the optimal number of clusters using the Elbow Method

Implementing K-Means Clustering with NumPy

Dimensionality
 Reduction

Feature Selection techniques (Filter, Wrapper, and Embedded methods)

Principal Component Analysis (PCA): Theory and mathematical foundation

Singular Value Decomposition (SVD) and its applications

Implementing PCA for dimensionality reduction with NumPy

Neural Networks: 
Introduction and Basics

Introduction to Neural Networks and their architecture

Single-layer Perceptrons: Activation functions and learning

Multi-layer Perceptrons (MLPs): Backpropagation algorithm

Implementing MLPs for simple tasks with libraries like Keras

Convolutional
Neural Networks (CNNs)

Introduction to CNNs and their applications in image processing

Convolutional layers, pooling layers, and flattening

Introduction to Deep Learning and its real-world applications

Building and training a CNN for image classification using Keras

Tech Stack

Throughout the course, you will gain practical experience and proficiency in using these tools 

Write your awesome label here.
Write your awesome label here.
Write your awesome label here.
Write your awesome label here.
Write your awesome label here.
Write your awesome label here.
Write your awesome label here.
Write your awesome label here.
Write your awesome label here.

Prof. Sashikumaar Ganesan

Chair, Dept. Computational and Data Sciences
IISc Bangalore

Program Director

Prof. Sashi, a dedicated educator with extensive expertise, takes great pleasure in mentoring graduates and working professionals alike. He has delivered enlightening courses on Artificial Intelligence, Machine Systems and Industrializing ML (MLOps) to over 750 working professionals, earning admiration from students and industry experts.