ENTERPRISE

SCHOOL OF ARTIFICIAL INTELLIGENCE

AI Programming
with Python
Nanodegree Program Syllabus
Overview
Start using AI techniques and developing skills related to programming, linear algebra, and neural networks.

Learning Objectives

A graduate of this program will be able to:

• Utilize programming tools like Python, NumPy, and PyTorch

• Understand Calculus and linear algebra applications

• Perform key techniques of neural networks, including gradient descent and backpropagation

AI Programming with Python 2

Program information

Estimated Time Skill Level

3 months at 10hrs/week* Beginner

Prerequisites

Learner should have basic calculus knowledge, including how to calculate derivatives. Basic algebra and programming
knowledge will shorten the time to mastery.

Required Hardware/Software

Learners need access to a computer running OS X or Windows.

*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.

AI Programming with Python 3

 Course 1

Introduction to Python
Start coding with Python, drawing upon libraries and automation scripts to solve complex problems quickly.

Course Project

Use a Pre-trained Image Classifier to Identify Dog Breeds

In this project, learners will be testing their newly-acquired Python coding skills by using a trained image
classifier. They will need to use the trained neural network to classify images of dogs (by breeds) and
compare the output with the known dog breed classification. Learners will have a chance to build their own
functions, use command line arguments, test the runtime of the code, create a dictionary of lists, and more.

• Learn why we program.

Lesson 1
• Prepare for the course ahead with a detailed topic overview.
Why Python?
• Understand how programming in Python is unique.

• Understand how data types and operators are the building blocks for
programming in Python.
Lesson 2 • Use the following data types: integers, floats, booleans, strings, lists, tuples,
sets, and dictionaries.
Data Types & Operators
• Use the following operators: arithmetic, assignment, comparison, logical,
membership, and identity.

AI Programming with Python 4

 • Implement decision-making in your code with conditionals.

• Repeat code with for and while loops.

Lesson 3
• Exit a loop with break, and skip an iteration of a loop with continue.
Control Flow
• Use helpful built-in functions like zip and enumerate.

• Construct lists in a natural way with list comprehensions..

• Write your own functions to encapsulate a series of commands.

• Understand variable scope, i.e., which parts of a program variables can be

Lesson 4
referenced from.
Functions • Make functions easier to use with proper documentation.

• Use lambda expressions, iterators, and generators.

• Write and run scripts locally on your computer.

• Work with raw input from users.

Lesson 5
• Read and write files, handle errors, and import local scripts.
Scripting
• Use modules from the Python standard library and from third-party libraries.

• Use online resources to help solve problems.

Lesson 6 • Object-oriented programming provides a few benefits over procedural

programming. Learn the basics by understanding how to use Classes.
Classes

AI Programming with Python 5

 Course 2

Anaconda, Jupyter Notebook, NumPy, Pandas

& Matplotlib
Learn how to use all the key tools for working with data in Python: Jupyter Notebooks, NumPy, Anaconda, Pandas,
and Matplotlib.

Lesson 1 • Learn how to use Anaconda to manage packages and environments for use
with Python.
Anaconda

Lesson 2 • Learn how to use Jupyter Notebooks to create documents combining code,
text, images, and more.
Jupyter Notebooks

• Learn the value of NumPy and how to use it to manipulate data for AI
Lesson 3 problems.

Numpy Basics • Mini-Project: Use NumPy to mean normalize an darray and separate it into
several smaller ndarrays.

Lesson 4 • Learn to use Pandas to load and process data for machine learning problems.

Panda Basics • Mini-Project: Use Pandas to plot and get statistics from stock data.

Lesson 5 • Learn how to use Matplotlib to choose appropriate plots for one and two
variables based on the types of data you have.
Matplotlib Basics

AI Programming with Python 6

 Course 3

Linear Algebra Essentials

Learn the foundational math needed for AI success—vectors, linear transformations, and matrices—as well as the linear
algebra behind neural networks.

Lesson 1 • Learn the basics of the beautiful world of linear algebra and why it is such an
important mathematical tool.
Introduction

Lesson 2
• Learn about the basic building block of linear algebra.
Vectors

Lesson 3 • Learn how to scale and add vectors and how to visualize them in 2 and 3
dimensions.
Linear Combination

Lesson 4
• Learn what a linear transformation is and how is it directly related to matrices.
Linear Transformation & Learn how to apply the math and visualize the concept.
Metrices

Lesson 5
• Learn about the world of neural networks and see how it related directly to
Linear Algebra in Neural neural networks.
Networks

• Vectors Lab: Learn howto graph 2D and 3D vectors.

Lesson 6 • Linear Combinations Lab: Learn how to computationally determine a vector’s

span and solve a simple system of equations.
Labs
• Linear Mapping Lab: Learn how to solve problems computationally using
vectors and matrices.

AI Programming with Python 7

 Course 4

Calculus Essentials
Learn the foundations of calculus to understand how to train a neural network: plotting, derivatives, the chain rule, and more.
See how these mathematical skills visually come to life with a neural network example.

Lesson 1 • Visualize the essence of calculus. Learn why it is such a powerful concept in
mathematics.
Introduction

• Learn about the derivative, one of the most important tools in calculus.
Lesson 2
• See how a derivative can measure the steepness of a function and why it is
Derivates Through Geometry such an important indicator in the world of machine learning.

Lesson 3 • Learn how to find the derivative of a composition of two or more functions, a
very important tool in training a neural network.
Chain Rule & Dot Product

Lesson 4 • Learn more about derivatives while focusing on exponential and implicit
functions.
More on Derivatives

Lesson 5
• Learn about the formal definition of a derivative through understanding limits.
Limits

Lesson 6
• Learn about the inverse of a derivative: the integral.
Integration

Lesson 6 • Learn more about the world of neural networks and see how it relates directly
to calculus through an explicit example.
Calculus in Neural Networks

AI Programming with Python 8

 Course 5

Neural Networks
Gain a solid foundation in the latest trends in AI: neural networks, deep learning, and PyTorch.

Course Project

Create Your Own Image Classifier

Successful software developers need to know how to incorporate deep learning models into everyday
applications. Any device with a camera will be using image classification, object detection, and face
recognition, all based on deep learning models. In this project learners will implement an image
classification application. This application will train a deep learning model on a dataset of images. It will then
use the trained model to classify new images. First learners will develop their code in a Jupyter notebook to
ensure their training implementation works well. Then, they will convert their code into a Python application
that they will run from the command line of their system.

Lesson 1
• Acquire a solid foundation in deep learning and neural networks.
Introduction to Neural • Implement gradient descent and backpropagation in Python.
Networks

Lesson 2 • Learn about techniques for how to improve training of a neural network, such
as early stopping, regularization and dropout..
Training Neural Networks

Lesson 3
• Learn how to use PyTorch for building deep learning models.
Deep Learning with PyTorch

AI Programming with Python 9

Meet your instructors.

Ortal Arel
Instructor

Ortal Arel holds a PhD in computer engineering, and has been a professor and researcher in the
field of applied cryptography. She has worked on design and analysis of intelligent algorithms for
high-speed custom digital architectures.

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.

Juan Delgado
Computational Physicist

Juan is a computational physicist with a master’s degree 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.

Mat Leonard
Instructor

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

AI Programming with Python 10

Mike Yi
Content Developer

Mike is a content developerwith a BS in mathematics and statistics. He received his PhD in

cognitive science from the University of Irvine. Previously, he worked on Udacity’s Data Analyst
Nanodegree program as a support lead.

Grant Sanderson
Instructor

Grant Sanderson is the creator of the YouTube channel 3Blue1Brown, which is devoted to
teaching math visually, using a custom-built animation tool. He was previously a content creator
for Khan Academy.

Jennifer Staab
Statistician & Computer Scientist

Jennifer holds 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.

Juno Lee
Data Scientist at Looplist

As a data scientist at Looplist, Juno built neural networks to analyze and categorize product
images, a recommendation system to personalize shopping experiences for each user, and tools
to generate insight into user behavior.

Andrew Paster
Entrepreneur

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.

AI Programming with Python 11

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.

AI Programming with Python 12

Our proven approach for building
job-ready digital skills.

Pre-Assessments

Identify skills gaps.

• In-depth assessments benchmark your team’s current level of knowledge in key areas.

• Results are used to generate custom learning paths.

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.

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.

Dashboard & Reporting

Track course progress.

• Udacity’s enterprise management console simplifies management of bulk enrollments and
employee onboarding.

• Interactive views help achieve targeted results to increase retention and productivity.

• Maximize ROI while optimizing job readiness.

AI Programming with Python 13

Learn more at
udacity.com/enterprise →

12.02.22 | V1.0