This course will teach you how to build convolutional neural networks and apply it to image data. Thanks to deep learning, computer vision is working far better than just two years ago, and this is enabling numerous exciting applications ranging from safe autonomous driving, to accurate face recognition, to automatic reading of radiology images.
This course is part of the Deep Learning Specialization
Offered By
Deep Learning SpecializationDeepLearning.AIAbout this Course
917,433 recent views
Learner Career Outcomes
36%
started a new career after completing these courses
37%
got a tangible career benefit from this course
12%
got a pay increase or promotion
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Course 4 of 5 in the
Flexible deadlines
Reset deadlines in accordance to your schedule.
Intermediate Level
Approx. 20 hours to complete
English
Subtitles: Chinese (Traditional), Arabic, French, Portuguese (European), Chinese (Simplified), Italian, Vietnamese, Korean, German, Russian, Turkish, English, Spanish, Japanese
Skills you will gain
Facial Recognition SystemTensorflowConvolutional Neural NetworkArtificial Neural Network
Learner Career Outcomes
36%
started a new career after completing these courses
37%
got a tangible career benefit from this course
12%
got a pay increase or promotion
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Course 4 of 5 in the
Flexible deadlines
Reset deadlines in accordance to your schedule.
Intermediate Level
Approx. 20 hours to complete
English
Subtitles: Chinese (Traditional), Arabic, French, Portuguese (European), Chinese (Simplified), Italian, Vietnamese, Korean, German, Russian, Turkish, English, Spanish, Japanese
Offered by
DeepLearning.AI
Founded by Andrew Ng, DeepLearning.AI is an education technology company that develops a global community of AI talent.
Syllabus - What you will learn from this course
6 hours to complete
Foundations of Convolutional Neural Networks
Learn to implement the foundational layers of CNNs (pooling, convolutions) and to stack them properly in a deep network to solve multi-class image classification problems.
6 hours to complete
12 videos (Total 140 min), 4 readings, 3 quizzes
12 videos
Edge Detection Example11m
More Edge Detection7m
Padding9m
Strided Convolutions9m
Convolutions Over Volume10m
One Layer of a Convolutional Network16m
Simple Convolutional Network Example8m
Pooling Layers10m
CNN Example12m
Why Convolutions?9m
Yann LeCun Interview27m
4 readings
Strided convolutions *CORRECTION*1m
Simple Convolutional Network Example *CORRECTION*1m
CNN Example *CORRECTION*1m
Why Convolutions? *CORRECTION*1m
1 practice exercise
The basics of ConvNets30m
5 hours to complete
Deep convolutional models: case studies
Learn about the practical tricks and methods used in deep CNNs straight from the research papers.
5 hours to complete
11 videos (Total 99 min), 1 reading, 2 quizzes
11 videos
Classic Networks18m
ResNets7m
Why ResNets Work9m
Networks in Networks and 1x1 Convolutions6m
Inception Network Motivation10m
Inception Network8m
Using Open-Source Implementation4m
Transfer Learning8m
Data Augmentation9m
State of Computer Vision12m
1 reading
Inception Network Motivation *CORRECTION*1m
1 practice exercise
Deep convolutional models30m
4 hours to complete
Object detection
Learn how to apply your knowledge of CNNs to one of the toughest but hottest field of computer vision: Object detection.
4 hours to complete
10 videos (Total 85 min), 2 readings, 2 quizzes
10 videos
Landmark Detection5m
Object Detection5m
Convolutional Implementation of Sliding Windows11m
Bounding Box Predictions14m
Intersection Over Union4m
Non-max Suppression8m
Anchor Boxes9m
YOLO Algorithm7m
(Optional) Region Proposals6m
2 readings
Convolutional Implementation of Sliding Windows *CORRECTION*1m
YOLO algorithm *CORRECTION*1m
1 practice exercise
Detection algorithms30m
5 hours to complete
Special applications: Face recognition & Neural style transfer
Discover how CNNs can be applied to multiple fields, including art generation and face recognition. Implement your own algorithm to generate art and recognize faces!
5 hours to complete
11 videos (Total 76 min), 3 readings, 3 quizzes
11 videos
One Shot Learning4m
Siamese Network4m
Triplet Loss15m
Face Verification and Binary Classification6m
What is neural style transfer?2m
What are deep ConvNets learning?7m
Cost Function3m
Content Cost Function3m
Style Cost Function13m
1D and 3D Generalizations9m
3 readings
Triplet Loss *CORRECTION*1m
Face Verification and Binary Classification *CORRECTION*1m
Style Cost *CORRECTION*1m
1 practice exercise
Special applications: Face recognition & Neural style transfer30m
Reviews
TOP REVIEWS FROM CONVOLUTIONAL NEURAL NETWORKS
by RKSep 1, 2019
This is very intensive and wonderful course on CNN. No other course in the MOOC world can be compared to this course's capability of simplifying complex concepts and visualizing them to get intuition.
by OASep 3, 2020
Great course. Easy to understand and with very synthetized information on the most relevant topics, even though some videos repeat information due to wrong edition, everything is still understandable.
by RSDec 11, 2019
Great Course Overall One thing is that some videos are not edited properly so Andrew repeats the same thing, again and again, other than that great and simple explanation of such complicated tasks.
by AGJan 12, 2019
Great course for kickoff into the world of CNN's. Gives a nice overview of existing architectures and certain applications of CNN's as well as giving some solid background in how they work internally.
About the Deep Learning Specialization
If you want to break into AI, this Specialization will help you do so. Deep Learning is one of the most highly sought after skills in tech. We will help you become good at Deep Learning.
Frequently Asked Questions
When will I have access to the lectures and assignments?
What will I get if I subscribe to this Specialization?
Is financial aid available?
More questions? Visit the Learner Help Center.
