Udacity part of Accenture logo

Introduction to Machine Learning with Pytorch

Nanodegree Program

Build powerful machine learning models to make predictions and uncover hidden patterns. Start with foundational supervised learning algorithms, including linear regression, decision trees, naive Bayes, support vector machines (SVMs), and perceptrons, then evaluate your model performance with a variety of evaluation metrics. Then, you'll advance from perceptrons to deep neural networks in order to perform supervised learning on complex data sources such as images. Finally, you'll dive into unsupervised learning methods, including clustering and dimensionality reduction for customer segmentation. For each technique, you'll start by learning the underlying math, then implement real-world models with Python libraries, including PyTorch and scikit-learn.

Build powerful machine learning models to make predictions and uncover hidden patterns. Start with foundational supervised learning algorithms, including linear regression, decision trees, naive Bayes, support vector machines (SVMs), and perceptrons, then evaluate your model performance with a variety of evaluation metrics. Then, you'll advance from perceptrons to deep neural networks in order to perform supervised learning on complex data sources such as images. Finally, you'll dive into unsupervised learning methods, including clustering and dimensionality reduction for customer segmentation. For each technique, you'll start by learning the underlying math, then implement real-world models with Python libraries, including PyTorch and scikit-learn.

  • Intermediate

  • 2 months

  • Last Updated January 14, 2025

Skills you'll learn:

Naive bayes classifiersGaussian mixture models

Prerequisites:

Multivariable calculusData wranglingPython for data scienceBasic supervised machine learningIntermediate Python

Intermediate

2 months

Last Updated January 14, 2025

Skills you'll learn:

Naive bayes classifiers • Gaussian mixture models • Model evaluation • Support vector machines

Prerequisites:

Multivariable calculus • Data wrangling • Python for data science

Courses In This Program

Course 1 2 hours

Introduction to Machine Learning

Welcome to Machine learning with Pytorch

Lesson 1

Welcome to Machine Learning

Welcome to the Machine Learning Engineer Nanodegree program! Learn about the program structure and the projects you'll work on in this program.

Lesson 2

Getting Help

You are starting a challenging but rewarding journey! Take 5 minutes to read how to get help with projects and content.

Lesson 3

Setting Up Your Computer

In this lesson, get your computer set up with Python 3 using Anaconda, as well as setting up a text editor.

Course 2 3 weeks

Supervised Learning

In this course, you'll learn about different types of supervised learning and how to use them to solve real-world problems.

Lesson 1

Introduction to Supervised Learning

Before diving into the many algorithms of machine learning, it is important to take a step back and understand the big picture associated with the entire field.

Lesson 2

Linear Regression

Linear regression is one of the most fundamental algorithms in machine learning. In this lesson, learn how linear regression works!

Lesson 3

Perceptron Algorithm

The perceptron algorithm is an algorithm for classifying data. It is the building block of neural networks.

Lesson 4

Decision Trees

Decision trees are a structure for decision-making where each decision leads to a set of consequences or additional decisions.

Lesson 5

Naive Bayes

Naive Bayesian Algorithms are powerful tools for creating classifiers for incoming labeled data. Specifically Naive Bayes is frequently used with text data and classification problems.

Lesson 6

Support Vector Machines

Support vector machines are a common method used for classification problems. They have been proven effective using what is known as the 'kernel' trick!

Lesson 7

Ensemble Methods

Bagging and boosting are two common ensemble methods for combining simple algorithms to make more advanced models that work better than the simple algorithms would on their own.

Lesson 8

Model Evaluation Metrics

Learn the main metrics to evaluate models, such as accuracy, precision, recall, and more!

Lesson 9

Training and Tuning

Learn the main types of errors that can occur during training, and several methods to deal with them and optimize your machine learning models.

Lesson 10 • Project

Finding Donors Project

You've covered a wide variety of methods for performing supervised learning -- now it's time to put those into action!

Course 3 3 weeks

Introduction to Neural Networks with PyTorch

Learn the fundamentals of neural networks with Python and PyTorch, and then use your new skills to create your own image classifier—an application that will first train a deep learning model on a dataset of images and then use the trained model to classify new images.

Lesson 1

Course Introduction

Meet your instructors, get a short overview of what you'll be learning, check your prerequisites, and learn how to use the workspaces and notebooks found throughout the lessons.

Lesson 2

Introduction to Neural Networks

In this lesson, Luis will give you solid foundations on deep learning and neural networks. You'll also implement gradient descent and backpropagation in Python right here in the classroom.

Lesson 3

Implementing Gradient Descent

Mat will introduce you to a different error function and guide you through implementing gradient descent using numpy matrix multiplication.

Lesson 4

Training Neural Networks

Now that you know what neural networks are, in this lesson you will learn several techniques to improve their training.

Lesson 5

Deep Learning with PyTorch

Learn how to use PyTorch for building deep learning models.

Lesson 6 • Project

Create Your Own Image Classifier

In this project, you'll create your own image classifier and then train—and evaluate its performance—using one of the most classic and well-studied computer vision data sets, CIFAR-10.

Course 4 3 weeks

Unsupervised Learning

In this course, you'll learn how to apply unsupervised learning to solve real-world problems.

Lesson 1

Clustering

Clustering is one of the most common methods of unsupervised learning. Here, we'll discuss the K-means clustering algorithm.

Lesson 2

Hierarchical and Density Based Clustering

We continue to look at clustering methods. Here, we'll discuss hierarchical clustering and density-based clustering (DBSCAN).

Lesson 3

Gaussian Mixture Models and Cluster Validation

In this lesson, we discuss Gaussian mixture model clustering. We then talk about the cluster analysis process and how to validate clustering results.

Lesson 4

Dimensionality Reduction and PCA

Often we need to reduce a large number of features in our data to a smaller, more relevant set. Principal Component Analysis, or PCA, is a method of feature extraction and dimensionality reduction.

Lesson 5

Random Projection and ICA

In this lesson, we will look at two other methods for feature extraction and dimensionality reduction: Random Projection and Independent Component Analysis (ICA).

Lesson 6 • Project

Project: Identify Customer Segments

In this project, you'll apply your unsupervised learning skills to two demographics datasets, to identify segments and clusters in the population, and see how customers of a company map to them.

Course 5 1 minute

Congratulations!

Lesson 1

Congratulations!

You've now reached the end of this program!

(Optional) Course 6 2 weeks

Prerequisite: Python for Data Analysis

Lesson 1

Why Python Programming

Welcome to Introduction to Python! Here's an overview of the course.

Lesson 2

Data Types and Operators

Familiarize yourself with the building blocks of Python! Learn about data types and operators, built-in functions, type conversion, whitespace, and style guidelines.

Lesson 3

Control Flow

Build logic into your code with control flow tools! Learn about conditional statements, repeating code with loops and useful built-in functions, and list comprehensions.

Lesson 4

Functions

Learn how to use functions to improve and reuse your code! Learn about functions, variable scope, documentation, lambda expressions, iterators, and generators.

Lesson 5

Scripting

Set up your own programming environment to write and run Python scripts locally! Learn good scripting practices, interact with different inputs, and discover awesome tools.

Lesson 6

NumPy

Learn the basics of NumPy and how to use it to create and manipulate arrays.

Lesson 7

Pandas

Learn the basics of Pandas Series and DataFrames and how to use them to load and process data.

(Optional) Course 7 3 weeks

Prerequisite: SQL for Data Analysis

Lesson 1

Basic SQL

In this section, you will gain knowledge about SQL basics for working with a single table. You will learn the key commands to filter a table in many different ways.

Lesson 2

SQL Joins

In this lesson, you will learn how to combine data from multiple tables together.

Lesson 3

SQL Aggregations

In this lesson, you will learn how to aggregate data using SQL functions

Lesson 4

SQL Subqueries & Temporary Tables

In this lesson, you will learn about subqueries, a fundamental advanced SQL topic. This lesson will walk you through the appropriate applications of subqueries, the different types of subqueries, and review subquery syntax and examples.

Lesson 5

SQL Data Cleaning

Cleaning data is an important part of the data analysis process. You will be learning how to perform data cleaning using SQL in this lesson.

Lesson 6

SQL Window Functions

Window functions allow users to compare one row to another without doing any joins using one of the most powerful concepts in SQL data analysis.

Lesson 7

SQL Advanced JOINS & Performance Tuning

Learn advanced joins and how to make queries that run quickly across giant datasets. Most of the examples in the lesson involve edge cases, some of which come up in interviews.

(Optional) Course 8 2 hours

Prerequisite: Command Line Essentials

Lesson 1

Shell Workshop

The Unix shell is a powerful tool for developers of all sorts. In this lesson, you'll get a quick introduction to the very basics of using it on your own computer.

(Optional) Course 9 3 weeks

Prerequisite: Git & Github

Lesson 1

What is Version Control

Version control is an incredibly important part of a professional programmer's life. In this lesson, you'll learn about the benefits of version control and install the version control tool Git!

Lesson 2

Create a Git Repo

Now that you've learned the benefits of Version Control and gotten Git installed, it's time you learn how to create a repository.

Lesson 3

Review a Repo's History

Knowing how to review an existing Git repository's history of commits is extremely important. You'll learn how to do just that in this lesson.

Lesson 4

Add Commits to a Repo

A repository is nothing without commits. In this lesson, you'll learn how to make commits, write descriptive commit messages, and verify the changes you're about to save to the repository.

Lesson 5

Tagging, Branching, and Merging

Being able to work on your project in isolation from other changes will multiply your productivity. You'll learn how to do this isolated development with Git's branches.

Lesson 6

Undoing Changes

Help! Disaster has struck! You don't have to worry, though, because your project is tracked in version control! You'll learn how to undo and modify changes that have been saved to the repository.

Lesson 7

Working with Remotes

You'll learn how to create remote repositories on GitHub and how to get and send changes to the remote repository.

Lesson 8

Working on Another Developer's Repository

In this lesson, you'll learn how to fork another developer's project. Collaborating with other developers can be a tricky process, so you'll learn how to contribute to a public project.

Lesson 9

Staying in Sync with a Remote Repository

You'll learn how to send suggested changes to another developer by using pull requests. You'll also learn how to use the powerful `git rebase` command to squash commits together.

(Optional) Course 10 3 weeks

Additional Material: Python for Data Visualization

Lesson 1

Data Visualization in Data Analysis

In this lesson, see the motivations for why data visualization is an important part of the data analysis process and where it fits in.

Lesson 2

Design of Visualizations

Learn about elements of visualization design, especially to avoid those elements that can cause a visualization to fail.

Lesson 3

Univariate Exploration of Data

In this lesson, you will see how you can use matplotlib and seaborn to produce informative visualizations of single variables.

Lesson 4

Bivariate Exploration of Data

In this lesson, build up from your understanding of individual variables and learn how to use matplotlib and seaborn to look at relationships between two variables.

Lesson 5

Multivariate Exploration of Data

In this lesson, see how you can use matplotlib and seaborn to visualize relationships and interactions between three or more variables.

Lesson 6

Explanatory Visualizations

Previous lessons covered how you could use visualizations to learn about your data. In this lesson, see how to polish up those plots to convey your findings to others!

Lesson 7

Visualization Case Study

Put to practice the concepts you've learned about exploratory and explanatory data visualization in this case study on factors that impact diamond prices.

(Optional) Course 11 1 month

Additional Material: Statistics for Data Analysis

Lesson 1

Descriptive Statistics - Part I

In this lesson, you will learn about data types, measures of center, and the basics of statistical notation.

Lesson 2

Descriptive Statistics - Part II

In this lesson, you will learn about measures of spread, shape, and outliers as associated with quantitative data. You will also get a first look at inferential statistics.

Lesson 3

Admissions Case Study

Learn to ask the right questions, as you learn about Simpson's Paradox.

Lesson 4

Probability

Gain the basics of probability using coins and die.

Lesson 5

Binomial Distribution

Learn about one of the most popular distributions in probability - the Binomial Distribution.

Lesson 6

Conditional Probability

Not all events are independent. Learn the probability rules for dependent events.

Lesson 7

Bayes Rule

Learn one of the most popular rules in all of statistics - Bayes rule.

Lesson 8

Python Probability Practice

Take what you have learned in the last lessons and put it to practice in Python.

Lesson 9

Normal Distribution Theory

Learn the mathematics behind moving from a coin flip to a normal distribution.

Lesson 10

Sampling distributions and the Central Limit Theorem

Learn all about the underpinning of confidence intervals and hypothesis testing - sampling distributions.

Lesson 11

Confidence Intervals

Learn how to use sampling distributions and bootstrapping to create a confidence interval for any parameter of interest.

Lesson 12

Hypothesis Testing

Learn the necessary skills to create and analyze the results in hypothesis testing.

Lesson 13

Case Study: A/B tests

Work through a case study of how A/B testing works for an online education company called Audacity.

Lesson 14

Regression

Use python to fit linear regression models, as well as understand how to interpret the results of linear models.

Lesson 15

Multiple Linear Regression

Learn to apply multiple linear regression models in python. Learn to interpret the results and understand if your model fits well.

Lesson 16

Logistic Regression

Learn to apply logistic regression models in python. Learn to interpret the results and understand if your model fits well.

(Optional) Course 12 4 hours

Additional Material: Linear Algebra

Lesson 1

Introduction

Take a sneak peek into the beautiful world of Linear Algebra and learn why it is such an important mathematical tool.

Lesson 2

Vectors

Learn about vectors, the basic building block of Linear Algebra.

Lesson 3

Linear Combination

Learn how to scale and add vectors and how to visualize the process.

Lesson 4

Linear Transformation and Matrices

What is a linear transformation and how is it directly related to matrices? Learn how to apply the math and visualize the concept.

Taught By The Best

Photo of Josh Bernhard

Josh Bernhard

Staff Data Scientist

Josh has been sharing his passion for data for over a decade. He's used data science for work ranging from cancer research to process automation. He recently has found a passion for solving data science problems within marketplace companies.

Photo of Mat Leonard

Mat Leonard

Content Developer

Mat is a former physicist, research neuroscientist, and data scientist. He did his PhD and Postdoctoral Fellowship at the University of California, Berkeley.

Photo of Andrew Paster

Andrew Paster

Instructor

Andrew has an engineering degree from Yale, and has used his data science skills to build a jewelry business from the ground up. He has additionally created courses for Udacity's Self-Driving Car Engineer Nanodegree program.

Photo of Jennifer Staab

Jennifer Staab

Instructor

Jennifer has a PhD in Computer Science and a Masters in Biostatistics; she was a professor at Florida Polytechnic University. She previously worked at RTI International and United Therapeutics as a statistician and computer scientist.

Photo of Dan Romuald Mbanga

Dan Romuald Mbanga

Instructor

Dan leads Amazon AI's Business Development efforts for Machine Learning Services. Day to day, he works with customers—from startups to enterprises—to ensure they are successful at building and deploying models on Amazon SageMaker.

Photo of Cezanne Camacho

Cezanne Camacho

Curriculum Lead

Cezanne is an expert in computer vision with a Masters in Electrical Engineering from Stanford University. As a former researcher in genomics and biomedical imaging, she's applied computer vision and deep learning to medical diagnostic applications.

Photo of Sean Carrell

Sean Carrell

Instructor

Sean Carrell is a former research mathematician specializing in Algebraic Combinatorics. He completed his PhD and Postdoctoral Fellowship at the University of Waterloo, Canada.

Photo of Jay Alammar

Jay Alammar

Instructor

Jay is a software engineer, the founder of Qaym (an Arabic-language review site), and the Investment Principal at STV, a $500 million venture capital fund focused on high-technology startups.

Photo of Luis Serrano

Luis Serrano

Instructor

Luis was formerly a Machine Learning Engineer at Google. He holds a PhD in mathematics from the University of Michigan, and a Postdoctoral Fellowship at the University of Quebec at Montreal.

Student Reviews

Average Rating: 4.7 Stars

248 Reviews

abdulrahman a.

July 19, 2022

everything were explained very well

Omer A.

April 27, 2022

Decent.

Narendhra Kumar M.

March 11, 2022

Good , yes Definitely but would need more time to understand the concepts in details. Because we are learning a lot of concepts

Abdullah A.

March 9, 2022

everything is great and makes me want to learn more ! but at the first 3 weeks i had faced some issues in my class room that stopped my learning. i tried to solve this problem by myself but i couldn't find any solution. i tried to send a ticket but web q/a provided me invalid solution, at the end i found out about udacity support account on twitter, i contacted them and by the way Brittany was a nice person. she sent a ticket to support on 27/1/2022. In 9/2/2022, Brittany contacted me and said problem was solved and everything should be ok. This problem/issue took from me many days of learning and i am afraid of the remaining time limit.

Rohit A.

March 7, 2022

yup pretty good, the projects also well designed. Although the instructor notes are missing from some of the deep learning lectures

Page 1 of 50

The Udacity Difference

Combine technology training for employees with industry experts, mentors, and projects, for critical thinking that pushes innovation. Our proven upskilling system goes after success—relentlessly.

Demonstrate proficiency with practical projects

Projects are based on real-world scenarios and challenges, allowing you to apply the skills you learn to practical situations, while giving you real hands-on experience.

  • Gain proven experience

  • Retain knowledge longer

  • Apply new skills immediately

Top-tier services to ensure learner success

Reviewers provide timely and constructive feedback on your project submissions, highlighting areas of improvement and offering practical tips to enhance your work.

  • Get help from subject matter experts

  • Learn industry best practices

  • Gain valuable insights and improve your skills

Enroll in Introduction to Machine Learning with Pytorch. Choose the plan that works for you

All Access monthly

  • Unlimited access to our top-rated courses

  • Personalized Career Services

  • Cancel Anytime

  • Real-world projects

  • Personalized project reviews

  • Program certificates

Best Value

All Access bundle1

  • All the same great benefits as our monthly plan

  • The most cost-effective way to develop the skills you want

  1. 1Discount applies to the first 4 months of membership, after which plans are converted to month-to-month.

Your subscription also includes:

Udacity Accenture logo

Company

  • Facebook
  • Twitter
  • LinkedIn
  • Instagram

© 2011-2025 Udacity, Inc. "Nanodegree" is a registered trademark of Udacity. © 2011-2025 Udacity, Inc.
We use cookies and other data collection technologies to provide the best experience for our customers.