Machine Learning

O.P. Jindal Global University via Coursera

Go to class Write review

Details

Go to class

Provider

Coursera
Pricing

Paid Course
Languages

English
Certificate

Certificate Available
Effort

11 weeks, 3 hours a week
Sessions

Self-Paced
Level

Beginner
Subtitles

English, Arabic, German, Korean, Portuguese, Japanese, Italian, French, Hungarian, Spanish

Found in

Overview

Google, IBM & Meta Certificates – 40% Off

One Coursera Plus subscription covers most Professional Certificates on Coursera.

Unlock All Certificates

Ready to turn data into smarter decisions? This advanced Machine Learning course is designed for learners with basic Python skills and experience with predictive tools who want to build practical machine learning expertise and move toward roles in business analytics, data engineering, or data science. You’ll learn how to frame real-world business problems as machine learning tasks and build, evaluate, and improve models using Python. Start with essential data science tools—including NumPy, pandas, and Matplotlib—then progress through classification, regression, clustering, and model evaluation with scikit-learn. Go beyond traditional machine learning with hands-on neural networks and deep learning using TensorFlow. Explore regression and classification, hyperparameter tuning, overfitting, sentiment analysis, natural language processing (NLP), word embeddings, convolutional neural networks (CNNs), and image classification. By the end, you’ll be equipped to apply machine learning algorithms to structured and unstructured data, interpret datasets, and draw meaningful management insights. Build the practical Python, machine learning, and deep learning skills you need to tackle data-driven business challenges and advance your career in data science.

Syllabus

Python for Data Science
- Welcome to the Machine Learning course! In this course, you will gain an in-depth introduction to building machine-learning models using Python. In this course, you will initially recapitulate the key Python libraries which are useful for Data Science applications. This includes coverage of Python libraries like Matplotlib, NumPy, and pandas. Next, you are introduced to the basics of machine learning, and the various classification and regression techniques are discussed. Also, the implementation of these techniques using the popular scikit-learn package is covered in detail. Artificial neural networks and the concept of deep learning is next explored with hands-on implementation of regression and classification algorithms using TensorFlow. As businesses increasingly draw insights from unstructured data (text, images, etc.), you would also get insights into neural networks-based deep learning models for the analysis of text and images. This is an advanced-level course, intended for learners with a background using predictive tools and techniques, and a basic understanding of Python programming concepts. The knowledge you gain from this course will help your career as a business analyst or a data engineer and even work toward becoming a data scientist. You will gain skills to apply machine learning algorithms to structured and unstructured data to draw management insights. Data science is an exciting new field used by various organizations to perform data-driven decisions. It is a combination of technical knowledge, mathematics, and business. In this module, we will use Python, one of the most popular languages among all the languages used by data scientists. We will also understand various topics of data science and how to apply them in a real-world scenario.
Weekly Summative Assessment: Python for Data Science
- This assessment is a graded quiz based on the modules covered this week.
Introduction to Machine Learning
- In this module, you will learn about the origin and evolution of machine learning. You will also learn the different ways a machine can learn, and the essential components needed to develop a machine-learning model. You will get an overview of different types of algorithms that you can use to train machine-learning models for specific business problems. The nature and type of data needed to train these algorithms will also be discussed. The module also discusses the different real-world and business best practices and challenges one will have to be sensitive to while deploying machine learning to support business operations.
Building Machine Learning Models Using Python
- In this module, you will re-examine several machine learning models. We will discuss hands-on tasks that machine learning is commonly applied to, and you will learn to measure the performance of machine learning systems. We will work with a popular library for the Python programming language called scikit-learn, which has assembled state-of-the-art implementations of many machine learning algorithms.
Weekly Summative Assessment: Building Machine Learning Models Using Python
- This assessment is a graded quiz based on the modules covered this week.
Artificial Neural Network
- In this module, you will learn about artificial neural networks (ANNs) and their role in machine learning. You will also learn about the perceptron, the first real-world application based on neural networks. The concepts of weights, biases, and activation functions along with their role in analyzing data and training of ANNs will be discussed. We will also discuss how concepts like backpropagation and gradient descent affect the process of learning with ANNs.
Implementing Neural Networks and Deep Learning Using Python
- In this module, you will learn about using neural network technique for predictive tasks. You will also learn how to use the Python open source TensorFlow machine learning library for implementing regression and classification models to draw insights from structured and unstructured text data. The module also discusses methods for hyperparameter tuning for performance improvement. Lastly, this module will help you to define deep learning models and look at the problem of overfitting and look at ways to identify and overcome it.
Weekly Summative Assessment: Implementing Neural Networks and Deep Learning Using Python
- This assessment is a graded quiz based on the module covered this week.
Natural Language Processing and Image Classification
- In this module, you will be introduced to the concept of word and image embeddings which are transforming natural language and image processing applications. You will learn how to generate word embeddings using a corpus of text and also use pre trained word embeddings like Glove and Fasttext. This module will also discuss convolution neural networks and image vector-based models for image classification tasks.
Weekly Summative Assessment: Natural Language Processing and Image Classification
- This assessment is a graded quiz based on the modules covered this week.
Term-End Individual Assignment
- This module describes the learning objectives, and submission instructions for the End-term Assignment for the course.