NANODEGREE PROGR AM SYLL ABUS

Intro to Machine
Learning with
TensorFlow
Overview
The ultimate goal of the Intro to Machine Learning with TensorFlow Nanodegree program is to help
students learn machine learning techniques such as data transformation and algorithms that can find
patterns in data and apply machine learning algorithms to tasks of their own design.

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.

I N CO L L A B O R AT I O N W I T H

Estimated Time: Prerequisites:

3 Months at Intermediate
10 hours / week Python

Flexible Learning: Technical Mentor

Self-paced, so Support:
you can learn on Our knowledgeable
the schedule that mentors guide your
works best for you learning and are
focused on answering
your questions,
motivating you and
keeping you on track

Intro to Machine Learning with TensorFlow | 2

To optimize your chances of success in this program, we recommend having experience with:

Intermediate Python programming knowledge, including:

• At least 40 hours of programming experience
• Familiarity with data structures like dictionaries and lists
• Experience with libraries like NumPy and pandas

Basic knowledge of probability and statistics, including:

• Experience calculating the probability of an event
• Familiarity with terms like the mean and variance of a probability distribution

There are a few courses that can help prepare you for this program, depending on the areas you need to
address. For example:

• AI Programming with Python Nanodegree Program

• Intro to Programming Nanodegree Program

One of our main goals at Udacity is to help you create a job-ready portfolio of completed projects.
Building a project is one of the best ways to test the skills you’ve acquired and to demonstrate your
newfound abilities to future employers or colleagues. Throughout this Nanodegree program, you’ll have the
opportunity to prove your skills by building the following projects:

• Finding Donors for CharityML: Apply supervised learning techniques on data collected for the US census to
help CharityML (a fictitious charity organization) identify groups of people that are most likely to donate to
their cause.

• Create Your Own Image Classifier: Define and train a neural network in TensorFlow that learns to classify
images; going from image data exploration to network training and evaluation.

• Identify Customer Segments with Arvato: Study a real dataset of customers for a company, and apply
several unsupervised learning techniques in order to segment customers into similar groups and extract
information that may be used for marketing or product improvement.

Your completed projects will become part of a career portfolio that will demonstrate to potential employers that
you have skills in data analysis and feature engineering, machine learning algorithms, and training and evaluating
models. In the sections below, you’ll find detailed descriptions of each project, along with the course material that
presents the skills required to complete the project.

Intro to Machine Learning with TensorFlow | 3

Course 1: Supervised Learning
In this course, you will learn about supervised learning, a common class of methods for model construction.

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
Course Project California, but to only those most likely to donate to the charity. Your
goal will be to evaluate and optimize several different supervised
Find Donors for CharityML learning algorithms to determine which algorithm will provide the
highest donation yield while under some marketing constraints.
The key skills demonstrated will include supervised learning,
model evaluation and comparison, and tuning models according to
constraints.

LEARNING OUTCOMES

• Learn the difference between Regression and Classification

LESSON ONE Regression • Train a Linear Regression model to predict values
• Learn to predict states using Logistic Regression

• Learn the definition of a perceptron as a building block for

Perceptron
LESSON TWO neural networks, and the perceptron algorithm for
Algorithms
classification.

• Train Decision Trees to predict states

LESSON THREE Decision Trees
• Use Entropy to build decision trees, recursively

Intro to Machine Learning with TensorFlow | 4

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

• Learn to train a Support Vector Machines to separate data,

Support Vector linearly
LESSON FIVE
Machines • Use Kernel Methods in order to train SVMs on data that is
not linearly separable

• Build data visualizations for quantitative and

categorical data.
Ensemble of
LESSON SIX • Create pie, bar, line, scatter, histogram, and
Learners
boxplot charts.
• Build professional presentations.

• Learn about different metrics to measure model success.

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

• Train and test models with Scikit-learn.

Training and Tuning
LESSON EIGHT • Choose the best model using evaluation techniques like
Models
cross-validation and grid search.

Intro to Machine Learning with TensorFlow | 5

Course 2: Neural Networks
In this course, you will learn the foundations of neural network design and training in TensorFlow.

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
Course Project new images. You will develop your code in a Jupyter notebook to
Build an Image Classifier ensure your implementation works well. Key skills demonstrated
include TensorFlow and neural networks, and model validation and
evaluation.

LEARNING OUTCOMES

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

Implementing
• Implement gradient descent using NumPy matrix
LESSON TWO Gradient
multiplication.
Descent

• Learn several techniques to effectively train a neural network.

Training Neural
LESSON THREE • Prevent overfitting of training data and learn best practices for
Networks
minimizing the error of a network.

Deep Learning with • Learn how to use TensorFlow for building deep learning
LESSON FOUR
TensorFlow models.

Intro to Machine Learning with TensorFlow | 6

Course 3: Unsupervised Learning
In this course, you will learn to implement unsupervised learning methods for different kinds of problem
domains.

In this project, you 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. You will first explore and pre-process the data by
scaling each product category and then identifying (and removing)
Course Project unwanted outliers. With the cleaned customer spending data, you
Create Customer Segments will apply PCA transformations to the data and implement clustering
algorithms to segment the transformed customer data. Finally, you
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, and unsupervised
clustering.

LEARNING OUTCOMES

• Learn the basics of clustering data

LESSON ONE Clustering
• Cluster data with the K-means algorithm

Hierarchical and • Cluster data with Single Linkage Clustering.

LESSON TWO Density-Based • Cluster data with DBSCAN, a clustering method that captures
Clustering the insight that clusters are dense group of points

• Cluster data with Gaussian Mixture Models

Gaussian Mixture
LESSON THREE • Optimize Gaussian Mixture Models with and Expectation
Models
Maximization

Dimensionality • Reduce the dimensionality of the data using Principal

LESSON FOUR
Reduction • Component Analysis and Independent Component Analysisv

Intro to Machine Learning with TensorFlow | 7

Our Classroom Experience
REAL-WORLD PROJECTS
Build your skills through industry-relevant projects. Get
personalized feedback from our network of 900+ project
reviewers. Our simple interface makes it easy to submit
your projects as often as you need and receive unlimited
feedback on your work.

KNOWLEDGE
Find answers to your questions with Knowledge, our
proprietary wiki. Search questions asked by other students,
connect with technical mentors, and discover in real-time
how to solve the challenges that you encounter.

WORKSPACES
See your code in action. Check the output and quality of
your code by running them on workspaces that are a part
of our classroom.

QUIZZES
Check your understanding of concepts learned in the
program by answering simple and auto-graded quizzes.
Easily go back to the lessons to brush up on concepts
anytime you get an answer wrong.

CUSTOM STUDY PLANS

Create a custom study plan to suit your personal needs
and use this plan to keep track of your progress toward
your goal.

PROGRESS TRACKER
Stay on track to complete your Nanodegree program with
useful milestone reminders.

Intro to Machine Learning with TensorFlow | 8

Learn with the Best

Luis Serrano Cezanne Camacho

I N S T R U C TO R
C U R R I C U LU M L E A D
Luis was formerly a Machine Learning Cezanne is a machine learning educator
Engineer at Google. He holds a PhD in with a Masters in Electrical Engineering
mathematics from the University of from Stanford University. As a former
Michigan, and a Postdoctoral Fellowship researcher in genomics and biomedical
at the University of Quebec at Montreal. imaging, she’s applied machine learning to
medical diagnostic applications.

Dan Romuald Mbanga Mat Leonard

I N S T R U C TO R I N S T R U C TO R
Dan leads Amazon AI’s Business Mat is a former physicist, research
Development efforts for Machine Learning neuroscientist, and data scientist. He did
Services. Day to day, he works with his PhD and Postdoctoral Fellowship at the
customers—from startups to enterprises— University of California, Berkeley.
to ensure they are successful at building
and deploying models on Amazon
SageMaker.

Intro to Machine Learning with TensorFlow | 9

Learn with the Best

Jennifer Staab Sean Carrell

I N S T R U C TO R
I N S T R U C TO R
Jennifer has a PhD in Computer Science Sean Carrell is a former research
and a Masters in Biostatistics; she mathematician specializing in Algebraic
was a professor at Florida Polytechnic Combinatorics. He completed his PhD and
University. She previously worked at RTI Postdoctoral Fellowship at the University
International and United Therapeutics as of Waterloo, Canada.
a statistician and computer scientist.

Josh Bernhard Jay Alammar

DATA S C I E N T I S T I N S T R U C TO R
Josh has been sharing his passion for Jay has a degree in computer science, loves
data for nearly a decade at all levels of visualizing machine learning concepts, and
university, and as Lead Data Science is the Investment Principal at STV, a $500
Instructor at Galvanize. He’s used data million venture capital fund focused on
science for work ranging from cancer high-technology startups.
research to process automation.

Intro to Machine Learning with TensorFlow | 10

Learn with the Best

Michael Virgo Andrew Paster

I N S T R U C TO R
I N S T R U C TO R
Michael is a Content Developer at Udacity, Andrew has an engineering degree from
and is currently pursuing a Masters in CS. Yale and has used his data science skills to
After beginning his career in business, he build a jewelry business from the ground
utilized Udacity courses and Nanodegree up. He has created courses for Udacity’s
programs to build his technical skills, Self-Driving Car Engineer Nanodegree
eventually becoming a Self-Driving Car program as well.
Engineer at Udacity, before switching roles
to work on content.

Juan Delgado
I N S T R U C TO R
Juan is a computational physicist with a
Masters in Astronomy. He is finishing his
PhD in Biophysics. He previously worked
at NASA developing space instruments
and writing software to analyze large
amounts of scientific data using machine
learning techniques.

Intro to Machine Learning with TensorFlow | 11

All Our Nanodegree Programs Include:

EXPERIENCED PROJECT REVIEWERS

REVIEWER SERVICES

• Personalized feedback & line by line code reviews

• 1600+ Reviewers with a 4.85/5 average rating
• 3 hour average project review turnaround time
• Unlimited submissions and feedback loops
• Practical tips and industry best practices
• Additional suggested resources to improve

TECHNICAL MENTOR SUPPORT

MENTORSHIP SERVICES

• Questions answered quickly by our team of

technical mentors
• 1000+ Mentors with a 4.7/5 average rating
• Support for all your technical questions

PERSONAL CAREER SERVICES

C AREER SUPPORT

• Github portfolio review

• LinkedIn profile optimization

Intro to Machine Learning with TensorFlow | 12

Frequently Asked Questions
PROGR AM OVERVIE W

WHY SHOULD I ENROLL?

Machine learning is changing countless industries, from health care to
finance to market predictions. Currently, the demand for machine learning
engineers far exceeds the supply. In this program, you’ll apply machine
learning techniques to a variety of real-world tasks, such as customer
segmentation and image classification. This program is designed to teach
you foundational machine learning skills that data scientists and machine
learning engineers use day-to-day.

WHAT JOBS WILL THIS PROGRAM PREPARE ME FOR?

This program emphasizes practical coding skills that demonstrate your
ability to apply machine learning techniques to a variety of business and
research tasks. It is designed for people who are new to machine learning
and want to build foundational skills in machine learning algorithms
and techniques to either advance within their current field or position
themselves to learn more advanced skills for a career transition.

HOW DO I KNOW IF THIS PROGRAM IS RIGHT FOR ME?

This program assumes that you have had several hours of Python
programming experience. Other than that, the only requirement is that you
have a curiosity about machine learning. Do you want to learn more about
recommendation systems or voice assistants and how they work? If so, then
this program is right for you.

WHAT IS THE DIFFERENCE BETWEEN INTRO TO MACHINE LEARNING

WITH PYTORCH, AND INTRO TO MACHINE LEARNING WITH
TENSORFLOW NANODEGREE PROGRAMS?
Both Nanodegree programs begin with the scikit-learn machine learning
library, before pivoting to either PyTorch or TensorFlow in the Deep Learning
sections.

The only difference between the two programs is the deep learning
framework utilized for Project 2. As such, there are accompanying lessons
in each respective Nanodegree program that train you to develop machine
learning models in that deep learning framework. You will complete the
same project, Create an Image Classifier, in both Nanodegree programs - in
PyTorch in Intro to Machine Learning with PyTorch, and in TensorFlow for
Intro to Machine Learning with TensorFlow.

ENROLLMENT AND ADMISSION

DO I NEED TO APPLY? WHAT ARE THE ADMISSION CRITERIA?

No. This Nanodegree program accepts all applicants regardless of
experience and specific background.

Intro to Machine Learning with TensorFlow | 13

FAQs Continued
WHAT ARE THE PREREQUISITES FOR ENROLLMENT?
It is recommended that you have the following knowledge, prior to entering
the program:

Intermediate Python programming knowledge, including:

• At least 40 hours of programming experience

• Familiarity with data structures like dictionaries and lists
• Experience with libraries like NumPy and pandas is a plus

Basic knowledge of probability and statistics, including:

• Experience calculating the probability of an event

• Knowing how to calculate the mean and variance of a probability
distribution is a plus

IF I DO NOT MEET THE REQUIREMENTS TO ENROLL, WHAT SHOULD I DO?

You can still succeed in this program, even if you do not meet the suggested
requirements. There are a few courses that can help prepare you for the
program. For example:

• Intro to Data Science

• Intro to Programming Nanodegree program

DO I HAVE TO TAKE THE INTRO TO MACHINE LEARNING NANODEGREE

PROGRAM BEFORE ENROLLING IN THE MACHINE LEARNING ENGINEER
NANODEGREE PROGRAM?
No. Each program is independent of the other. If you are interested in
machine learning, you should look at the prerequisites for each program
to help you decide where you should start your journey to becoming a
machine learning engineer.

TUITION AND TERM OF PROGR AM

HOW IS THIS NANODEGREE PROGRAM STRUCTURED?

The Intro to Machine Learning with TensorFlow Nanodegree program is
comprised of content and curriculum to support three (3) projects. We
estimate that students can complete the program in three (3) months,
working 10 hours per week.

Each project will be reviewed by the Udacity reviewer network. Feedback

will be provided and if you do not pass the project, you will be asked to
resubmit the project until it passes.

Intro to Machine Learning with TensorFlow | 14

FAQs Continued
HOW LONG IS THIS NANODEGREE PROGRAM?
Access to this Nanodegree program runs for the length of time specified
in the payment card above. If you do not graduate within that time period,
you will continue learning with month to month payments. See the Terms
of Use and FAQs for other policies regarding the terms of access to our
Nanodegree programs.

I HAVE GRADUATED FROM THE BUSINESS ANALYTICS NANODEGREE

PROGRAM AND I WANT TO KEEP LEARNING. WHERE SHOULD I GO FROM
HERE?
Many of our graduates continue on to our Machine Learning Engineer
Nanodegree program, and after that, to the Self-Driving Car Engineer and
Artificial Intelligence Nanodegree programs.

SOF T WARE AND HARDWARE

WHAT SOFTWARE AND VERSIONS WILL I NEED IN THIS PROGRAM?

You will need 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.

Most modern Windows, OS X, and Linux laptops or desktop will work well;
we do not recommend a tablet since they typically have less computing
power. We will provide you with instructions to install the required software
packages.

You will use Python, Scikit-learn, TensorFlow (library in Python used in Deep
Learning project), Jupyter Notebook, NumPy, Anaconda, and Pandas in this
Nanodegree program.

Intro to Machine Learning with TensorFlow | 15