Convolutional Neural Networks

Ends soon! Save on skills that make you shine with 40% off 3 months of Coursera Plus. Save now

Convolutional Neural Networks

This course is part of Deep Learning Specialization

Instructors: Andrew Ng +2 more

Top Instructor

568,197 already enrolled

4 modules

Gain insight into a topic and learn the fundamentals.

42,585 reviews

Intermediate level

Recommended experience

Flexible schedule

4 weeks at 10 hours a week

Learn at your own pace

95%

Most learners liked this course

4 modules

Gain insight into a topic and learn the fundamentals.

42,585 reviews

Intermediate level

Recommended experience

Flexible schedule

4 weeks at 10 hours a week

Learn at your own pace

95%

Most learners liked this course

Skills you'll gain

Category: Model Training
Category: Image Analysis
Category: Convolutional Neural Networks
Category: Artificial Neural Networks
Category: Embeddings
Category: Transfer Learning
Category: Applied Machine Learning
Category: Data Preprocessing
Category: Deep Learning
Category: Computer Vision
Category: Network Architecture
Category: Fine-tuning

Tools you'll learn

Category: Tensorflow

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

4 assignments

Taught in English

91% of learners achieved a positive career outcome

Build your subject-matter expertise

This course is part of the Deep Learning Specialization

When you enroll in this course, you'll also be enrolled in this Specialization.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate

There are 4 modules in this course

In the fourth course of the Deep Learning Specialization, you will understand how computer vision has evolved and become familiar with its exciting applications such as autonomous driving, face recognition, reading radiology images, and more.

By the end, you will be able to build a convolutional neural network, including recent variations such as residual networks; apply convolutional networks to visual detection and recognition tasks; and use neural style transfer to generate art and apply these algorithms to a variety of image, video, and other 2D or 3D data. The Deep Learning Specialization is our foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. It provides a pathway for you to gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take the definitive step in the world of AI.

Implement the foundational layers of CNNs (pooling, convolutions) and stack them properly in a deep network to solve multi-class image classification problems.

What's included

12 videos6 readings1 assignment2 programming assignments

12 videosTotal 140 minutes

Computer Vision6 minutes
Edge Detection Example12 minutes
More Edge Detection8 minutes
Padding10 minutes
Strided Convolutions9 minutes
Convolutions Over Volume11 minutes
One Layer of a Convolutional Network16 minutes
Simple Convolutional Network Example9 minutes
Pooling Layers10 minutes
CNN Example13 minutes
Why Convolutions?10 minutes
Yann LeCun Interview28 minutes

6 readingsTotal 11 minutes

Join the DeepLearning.AI Forum to ask questions, get support, or share amazing ideas!2 minutes
Clarifications about Upcoming Simple Convolutional Network Example Video1 minute
Clarifications about Upcoming CNN Example Video1 minute
Clarifications about Upcoming Why Convolutions?1 minute
Lecture Notes W11 minute
(Optional) Downloading your Notebook, Downloading your Workspace and Refreshing your Workspace5 minutes

1 assignmentTotal 50 minutes

The Basics of ConvNets 50 minutes

2 programming assignmentsTotal 360 minutes

Convolutional Model, Step by Step180 minutes
Convolution Model Application180 minutes

Discover some powerful practical tricks and methods used in deep CNNs, straight from the research papers, then apply transfer learning to your own deep CNN.

What's included

14 videos3 readings1 assignment2 programming assignments

14 videosTotal 127 minutes

Why look at case studies?3 minutes
Classic Networks18 minutes
ResNets7 minutes
Why ResNets Work?9 minutes
Networks in Networks and 1x1 Convolutions6 minutes
Inception Network Motivation10 minutes
Inception Network9 minutes
MobileNet16 minutes
MobileNet Architecture9 minutes
EfficientNet4 minutes
Using Open-Source Implementation5 minutes
Transfer Learning9 minutes
Data Augmentation10 minutes
State of Computer Vision13 minutes

3 readingsTotal 3 minutes

Clarifications about Upcoming Inception Network Motivation Video1 minute
Lecture Notes W21 minute
Note on the Upcoming Programming Assignment - Residual Networks1 minute

1 assignmentTotal 50 minutes

Deep Convolutional Models 50 minutes

2 programming assignmentsTotal 360 minutes

Residual Networks180 minutes
Transfer Learning with MobileNet180 minutes

Apply your new knowledge of CNNs to one of the hottest (and most challenging!) fields in computer vision: object detection.

What's included

14 videos4 readings1 assignment2 programming assignments

14 videosTotal 110 minutes

Object Localization12 minutes
Landmark Detection6 minutes
Object Detection6 minutes
Convolutional Implementation of Sliding Windows11 minutes
Bounding Box Predictions14 minutes
Intersection Over Union4 minutes
Non-max Suppression8 minutes
Anchor Boxes10 minutes
YOLO Algorithm7 minutes
Region Proposals (Optional)6 minutes
Semantic Segmentation with U-Net7 minutes
Transpose Convolutions8 minutes
U-Net Architecture Intuition3 minutes
U-Net Architecture8 minutes

4 readingsTotal 13 minutes

Clarifications about Upcoming Convolutional Implementation of Sliding Windows Video1 minute
Clarifications about Upcoming YOLO Algorithm Video1 minute
Lecture Notes W31 minute
Clear Output Before Submitting (For U-Net Assignment)10 minutes

1 assignmentTotal 50 minutes

Detection Algorithms 50 minutes

2 programming assignmentsTotal 360 minutes

Car detection with YOLO180 minutes
Image Segmentation with U-Net180 minutes

Explore how CNNs can be applied to multiple fields, including art generation and face recognition, then implement your own algorithm to generate art and recognize faces!

What's included

11 videos6 readings1 assignment2 programming assignments

11 videosTotal 75 minutes

What is Face Recognition?5 minutes
One Shot Learning5 minutes
Siamese Network5 minutes
Triplet Loss15 minutes
Face Verification and Binary Classification6 minutes
What is Neural Style Transfer?2 minutes
What are deep ConvNets learning?8 minutes
Cost Function4 minutes
Content Cost Function4 minutes
Style Cost Function13 minutes
1D and 3D Generalizations9 minutes

6 readingsTotal 25 minutes

Clarifications about Upcoming Face Verification and Binary Classification Video1 minute
Clarifications about Upcoming Style Cost Function Video1 minute
Lecture Notes W41 minute
[IMPORTANT] Reminder about end of access to Lab Notebooks2 minutes
References10 minutes
Acknowledgments10 minutes

1 assignmentTotal 50 minutes

Special Applications: Face Recognition & Neural Style Transfer 50 minutes

2 programming assignmentsTotal 360 minutes

Face Recognition180 minutes
Art Generation with Neural Style Transfer180 minutes

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.

Instructors

Instructor ratings

(3,236 ratings)

Top Instructor

Andrew Ng

DeepLearning.AI

51 Courses9,750,672 learners

Offered by

DeepLearning.AI

Why people choose Coursera for their career

Felipe M.

Learner since 2018

"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."

Jennifer J.

Learner since 2020

"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."

Larry W.

Learner since 2021

"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."

Chaitanya A.

"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

Learner reviews

5 stars
87.83%
4 stars
10.27%
3 stars
1.40%
2 stars
0.28%
1 star
0.19%

Showing 3 of 42585

Reviewed on Aug 5, 2019

Great content in lectures! Automatic graders for programming assignments can be tricky, and set to old versions of tf sometimes, but answers to these issues are readily found in the discussion forums.

Reviewed on Jan 11, 2019

Amazing! Feels like AI is getting tamed in my hands. Course lectures , assignments are excellent. To those who are not well versed with python - numpy and tensorflow , it would be better to brush up.

Reviewed on May 5, 2019

A big thank you to Professor Andrew and his team for structuring this course and introducing the world of ConvNets to me. I found the video lectures easy to understand and the exercises intriguing.

Frequently asked questions

To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.

When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.