Back to Catalog

PyTorch Fundamentals for Machine Learning

IntermediateCourse

Learn the fundamentals of PyTorch for machine learning in this course. Topics include tensors, linear regression, logistic regression, and optimization techniques like gradient descent. Apply your skills through hands-on projects and quizzes.

Language

  • English

Topic

  • Machine Learning

Skills You Will Learn

  • PyTorch, Deep Learning, Machine Learning, Loss Functions, Multiple Linear Regression, Gradient Descent

Offered By

  • IBMSkillsNetwork

Estimated Effort

  • 17 Hours

Platform

  • SkillsNetwork

Last Update

  • May 1, 2025
About this Course

About this course

In this intermediate course, you’ll learn the essentials of PyTorch for machine learning techniques. Starting with tensors, you’ll understand their role in machine learning and how to perform basic operations with them. You’ll also explore differentiation in PyTorch, which is key for optimizing models. With hands-on labs, you’ll apply these concepts to work with simple and Torch Vision datasets, gaining experience in handling data for model training.
 
You’ll then move into regression techniques, beginning with linear regression, where you’ll learn how to predict outcomes and optimize models using gradient descent. You’ll understand key concepts like loss functions and the steps involved in model training, which will prepare you for more complex machine learning tasks.
 
The course will also cover more advanced regression techniques, including multiple input-output linear regression. You’ll learn how to handle multi-dimensional data, make predictions with multiple features and outputs, and train more sophisticated models.
 
Classification is another key area of focus, where you’ll dive into logistic regression and learn how to apply it to solve classification problems. Through exercises, you’ll explore how to use linear classifiers, apply loss functions like Cross Entropy Loss, and implement effective models for binary classification.
 
Finally, you’ll apply your learning to real-world problems. The practice project will involve building a neural network to classify breast cancer data, while the final project will challenge you to develop a League of Legends match predictor. You’ll work through data preparation, model building, and optimization, while receiving peer feedback to refine your skills.
 
By the end of the course, you’ll be equipped to build and optimize machine learning models with PyTorch, solving regression and classification problems efficiently and effectively. You’ll gain the experience necessary to tackle machine learning challenges and develop your skills further in this rapidly growing field.

What you will learn: 

After completing this course, you will be able to: 
  • Define tensors and understand their applications in PyTorch.
  • Explain linear regression and how to apply it using PyTorch.
  • Implement stochastic and mini-batch gradient descent algorithms.
  • Compare different methods of regression (linear, multiple) in terms of predictions and loss functions.
  • Assess the performance of a model using training, validation, and test splits.
  • Develop a final project that applies learned techniques to classify or predict outcomes in a dataset.

Course Syllabus

Module 1: Tensors 1D

Welcome
  • Video: Course Introduction
  • Reading: Course Overview
  • General Information
  • Learning Objectives and Syllabus
  • Grading Scheme
  • Helpful Tips for Course Completion
  • Video: Overview of Tensors 
Tensors 1D
  • Errata:Tensors ID
  • Video: Tensors 1D 
  • Reading: Tensors 1D 
  • Lab2: Tensors 1D 
Two-Dimensional Tensors
  • Errata:Two-Dimensional Tensors 
  • Video: Two-Dimensional Tensors 
  • Lab: Two-Dimensional Tensors 
Derivatives in PyTorch
  • Video: Differentiation in PyTorch 
  • Lab: Differentiation in PyTorch 
Simple Dataset
  • Video: Simple Dataset 
  • Lab: Simple Dataset
Dataset
  • Video: Dataset 
  • Lab: Dataset 
  • Lab: Torch Vision Datasets 
  • Module-level Graded Quiz: Tensor and Dataset

Module 2: Linear Regression

Linear Regression Prediction
  • Video: Linear Regression Prediction 
  • Lab: Linear Regression 1D: Prediction  
Linear Regression Training
  • Errata: Linear Regression Training  
  • Video: Linear Regression Training  
  • Video: Loss  
Gradient Descent and Cost
  • Video: Gradient Descent and Cost 
  • Video: Cost  
PyTorch Slope
  • Video: Linear Regression PyTorch 
  • Lab: Linear Regression ID: Training one Parameter
Linear Regression Training
  • Errata: PyTorch Linear Regression Training Slope and Bias  
  • Video: PyTorch Linear Regression Training Slope and Bias  
  • Lab: Linear Regression: Prediction 
  • Module-level Graded Quiz: Linear Regression

Module 3: Linear Regression PyTorch Way

Stochastic Gradient Descent and Data Loader
  • Video: Stochastic Gradient Descent  
  • Lab: Stochastic Gradient Descent and Data Loader   
Mini-Batch Gradient Descent
  • Video: Mini-Batch Gradient Descent  
  • Lab: Mini-Batch Gradient Descent  
Optimization in PyTorch
  • Video: Optimization in PyTorch 
  • Lab: Optimization in PyTorch 
Training, Validation, and Test Split
  • Video: Training, Validation, and Test Split 
  • Errata: Training, Validation, and Test Split PyTorch
  • Video: Training, Validation, and Test Split PyTorch 
  • Lab: Training, Validation, and Test Split in PyTorch 
  • Module-level Graded Quiz: Linear Regression PyTorch Way

Module 4: Multiple Input Output Linear Regression

Multiple Linear Regression Prediction
  • Video: Multiple Linear Regression Prediction 
  • Lab: Multiple Linear Regression Prediction 
  • Video: Multiple Linear Regression Training 
  • Lab: Multiple Linear Regression Training 
Multiple Output Linear Regression
  • Video: Linear Regression Multiple Outputs  
  • Lab: Multiple Linear Regression Prediction 
  • Video: Multiple Output Linear Regression Training 
  • Lab: Multiple Linear Regression Training 
  • Module-level Graded Quiz: Multiple Input Output Linear Regression 

Module 5: Logistic Regression for Classification

Linear Classier
  • Video: Linear Classifiers  
Logistic Regressioin Prediction
  • Video: Logistic Regression Prediction   
  • Lab: Logistic Regression Prediction  
Bernoulli Distribution and Maximum Likelihood Estimation
  • Video: Bernoulli Distribution and Maximum Likelihood Estimation 
Logistic Regression Cross Entropy Loss
  • Video: Logistic Regression Cross Entropy Loss    
  • Lab: Logistic Regression Mean Square Error 
  • Lab: Logistic Regression Cross Entropy  
  • Module-level Graded Quiz: Linear Classifiers

Module 6: Practice Project and Final Project

Practice Project and Final Project
  • Practice Project: Neural Network for Breast Cancer Classification
  • Reading: Final Project Overview
  • Final Project: League of Legends Match Predictor
  • Reading Peer-Review: Final Project League of Legends Match Predictor
Course Wrap-Up
  • Congratulations and Next Steps
  • Thanks from the Course Team
  • Reading: Copyrights and Trademarks

General Information

  • This course is self-paced. 
  • This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer, or Safari. 

Recommended Skills Prior to Taking this Course

The following skills are required to be successful with this course: 
  • High School level Mathematics
  • Working knowledge of Python.
  • Machine Learning with Python
  • Fundamentals of Deep Learning

Instructors

Joseph Santarcangelo

Senior Data Scientist at IBM

Joseph has a Ph.D. in Electrical Engineering, his research focused on using machine learning, signal processing, and computer vision to determine how videos impact human cognition. Joseph has been working for IBM since he completed his PhD.

Read more

Rav Ahuja

Global Program Director, IBM Skills Network

Rav Ahuja is a Global Program Director at IBM. He leads growth strategy, curriculum creation, and partner programs for the IBM Skills Network. Rav co-founded Cognitive Class, an IBM led initiative to democratize skills for in demand technologies. He is based out of the IBM Canada Lab in Toronto and specializes in instructional solutions for AI, Data, Software Engineering and Cloud. Rav presents at events worldwide and has authored numerous papers, articles, books and courses on subjects in managing and analyzing data. Rav holds B. Eng. from McGill University and MBA from University of Western Ontario.

Read more