INDIVIDUAL LEARNERS

SCHOOL OF ARTIFICIAL INTELLIGENCE

Intro to Machine
Learning with PyTorch
Nanodegree Program Syllabus
Overview
Learn machine learning techniques such as data transformation and algorithms that can find patterns in data. Learners will
apply these machine learning algorithms to tasks of their own designs. By the end of the program, they’ll have a portfolio that
features their newly acquired data analysis skills.

Learning Objectives

A graduate of this program will be able to:

• Use Python and SQL to access and analyze data from several different data sources.

• Build predictive models using a variety of unsupervised and supervised machine learning techniques.

• Perform feature engineering to improve the performance of machine learning models.

• Optimize, tune, and improve algorithms according to specific metrics like accuracy and speed.

• Compare the performances of learned models using suitable metrics.

Built in collaboration with:

Intro to Machine Learning with PyTorch 2

Program information

Estimated Time Skill Level

3 months at 10hrs/week* Intermediate

Prerequisites

Learners must have intermediate Python programming knowledge and basic understanding of probabilities and statistics.

Required Hardware/Software

Learners need access to a computer running a 64-bit operating system with at least 8GB of RAM, along with administrator
account permissions sufficient to install programs including Anaconda with Python 3.x and supporting packages.

*The length of this program is an estimation of total hours the average student may take to complete all required
coursework, including lecture and project time. If you spend about 5-10 hours per week working through the program, you
should finish within the time provided. Actual hours may vary.

Intro to Machine Learning with PyTorch 3

 Course 1

Supervised Learning
Learn about supervised learning, a common class of methods for model construction.

Course Project

Find Donors for CharityML

CharityML is a fictitious charity organization located in the heart of Silicon Valley that was established to
provide financial support for people eager to learn machine learning. To expand their potential donor base,
CharityML has decided to send letters to residents of California, but to only those most likely to donate to
the charity. The goal will be to evaluate and optimize several different supervised learning algorithms to
determine which algorithm will provide the highest donation yield while under some marketing constraints.

• Supervised learning

• Model evaluation and comparison

• Tuning models according to constraints

• Learn the difference between regression and classification.

Lesson 1
• Train a linear regression model to predict values.
Regression
• Learn to predict states using Logistic Regression.

Lesson 2 • Learn the definition of a perceptron as a building block for neural networks,
and the perceptron algorithm for classification.
Perceptron Algorithms

Intro to Machine Learning with PyTorch 4

Lesson 3 • Train decision trees to predict states.

Decision Trees • Use entropy to build decision trees, recursively.

• Learn Bayes’ rule, and apply it to predict cases of spam messages using the
Naive Bayes algorithm.
Lesson 4
• Train models using Bayesian learning.
Naive Bayes
• Complete an exercise that uses Bayesian learning for natural language
processing.

• Learn to train support vector machines to separate data, linearly.

Lesson 5
• Use Kernel methods in order to train SVMs on data that is not linearly
Support Vector Machines separable.

• Build data visualizations for quantitative and categorical data.

Lesson 6
• Create pie, bar, line, scatter, histogram, and boxplot charts.
Ensemble of Learners
• Build professional presentations.

• Learn about different metrics to measure model success.

Lesson 7
• Calculate accuracy, precision, and recall to measure the performance of your
Evaluation Metrics models.

• Train and test models with Scikit-learn.

Lesson 8
• Choose the best model using evaluation techniques like cross-validation and
Training & Tuning Models grid search.

Intro to Machine Learning with PyTorch 5

 Course 2

Introduction to Neural Networks with PyTorch

Implementing an image classification application using a deep neural network. This application will train a deep learning model
on a dataset of images. It will then use the trained model to classify new images. Learners will develop their code in a Jupyter
notebook to ensure your implementation works well.

Course Project

Create Your Own Image Classifier

As a machine learning engineer at a fictional self-driving car startup, learners have been asked to help
decide whether to build or buy an object detection algorithm for objects that may be on the side of the
road. A company, Detectocorp, claims an 80% accuracy rate on the CIFAR-10 dataset, a benchmark used to
evaluate the state of the art for computer vision systems.

Learners will try their hand at training a neural network to recognize objects in images and evaluate the
model’s performance compared to Detectocorp’s model.

Lesson 1
• Learn the foundations of deep learning and neural networks.
Introduction to Neural • Implement gradient descent and backpropagation in Python.
Networks

Lesson 2

• Implement gradient descent using NumPy matrix multiplication.

Implementing Gradient
Descent

Intro to Machine Learning with PyTorch 6

 • Learn several techniques to effectively train a neural network.
Lesson 3
• Prevent overfitting of training data and learn best practices for minimizing the
Training Neural Networks error of a network.

Lesson 4
• Learn how to use PyTorch for building deep learning models.
Deep Learning with PyTorch

Course 3

Unsupervised Learning
Learn to implement unsupervised learning methods for different kinds of problem domains.

Course Project

Creating Customer Segments

In this project, learners will apply unsupervised learning techniques on product spending data collected
for customers of a wholesale distributor in Lisbon, Portugal to identify customer segments hidden in
the data. Learners will first explore and pre-process the data by scaling each product category and then
identifying (and removing) unwanted outliers. With the cleaned customer spending data, they will apply PCA
transformations to the data and implement clustering algorithms to segment the transformed customer
data. Finally, they will compare the segmentation found with an additional labeling and consider ways this
information could assist the wholesale distributor with future service changes. Key skills demonstrated
include:

• Data cleaning

• Dimensionality reduction with PCA

• Unsupervised clustering

Intro to Machine Learning with PyTorch 7

Lesson 1 • Learn the basics of clustering data.

Clustering • Cluster data with the K-means algorithm.

Lesson 2 • Cluster data with single linkage clustering.

Hierarchical & Density-Based • Cluster data with DBSCAN, a clustering method that captures the insight that

Clustering clusters are dense group of points.

Lesson 3 • Cluster data with Gaussian mixture models.

Gaussian Mixture Models • Optimize Gaussian mixture models with and expectation maximization.

Lesson 4 • Reduce the dimensionality of the data using principal.

Dimensionality Reduction • Component analysis and independent component analysis.

Intro to Machine Learning with PyTorch 8

Meet your instructors.

Luis Serrano
Machine Learning Engineer

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.

Cezanne Camacho
Curriculum Lead

Cezanne is a machine learning educator with a master’s degree in electrical engineering from
Stanford University. As a former researcher in genomics and biomedical imaging, she’s applied
machine learning to medical diagnostic applications.

Dan Romuald Mbanga

Head of Product Strategy, ML

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.

Mat Leonard
Instructor

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

Intro to Machine Learning with PyTorch 9

Jennifer Staab
Instructor

Jennifer has a PhD in computer science and a master’s 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.

Sean Carrell
Research Mathematician

Sean Carrell is a former research mathematician specializing in algebraic combinatorics. He

completed his PhD and postdoctoral fellowship at the University of Waterloo, Canada.

Josh Bernhard
Data Scientist

Josh has been sharing his passion for data for nearly a decade at all levels of university, and as Lead
Data Science Instructor at Galvanize. He’s used data science for work ranging from cancer research
to process automation.

Intro to Machine Learning with PyTorch 10

Udacity’s learning
experience

Hands-on Projects Quizzes

Open-ended, experiential projects are designed Auto-graded quizzes strengthen comprehension.
to reflect actual workplace challenges. They aren’t Learners can return to lessons at any time during
just multiple choice questions or step-by-step the course to refresh concepts.
guides, but instead require critical thinking.

Knowledge Custom Study Plans

Find answers to your questions with Knowledge, Create a personalized study plan that fits your
our proprietary wiki. Search questions asked by individual needs. Utilize this plan to keep track of
other students, connect with technical mentors, movement toward your overall goal.
and discover how to solve the challenges that
you encounter.

Workspaces Progress Tracker

See your code in action. Check the output and Take advantage of milestone reminders to stay
quality of your code by running it on interactive on schedule and complete your program.
workspaces that are integrated into the platform.

Intro to Machine Learning with PyTorch 11

Our proven approach for building
job-ready digital skills.
Experienced Project Reviewers

Verify skills mastery.

• Personalized project feedback and critique includes line-by-line code review from
skilled practitioners with an average turnaround time of 1.1 hours.

• Project review cycle creates a feedback loop with multiple opportunities for
improvement—until the concept is mastered.

• Project reviewers leverage industry best practices and provide pro tips.

Technical Mentor Support

24/7 support unblocks learning.

• Learning accelerates as skilled mentors identify areas of achievement and potential
for growth.

• Unlimited access to mentors means help arrives when it’s needed most.

• 2 hr or less average question response time assures that skills development stays on track.

Personal Career Services

Empower job-readiness.
• Access to a Github portfolio review that can give you an edge by highlighting your
strengths, and demonstrating your value to employers.*

• Get help optimizing your LinkedIn and establishing your personal brand so your profile
ranks higher in searches by recruiters and hiring managers.

Mentor Network

Highly vetted for effectiveness.

• Mentors must complete a 5-step hiring process to join Udacity’s selective network.

• After passing an objective and situational assessment, mentors must demonstrate

communication and behavioral fit for a mentorship role.

• Mentors work across more than 30 different industries and often complete a Nanodegree
program themselves.

*Applies to select Nanodegree programs only.

Intro to Machine Learning with PyTorch 12

Learn more at
www.udacity.com/online-learning-for-individuals →

04.05.23 | V2.0