We may earn an affiliate commission when you visit our partners.

Convolutional Neural Networks

Andrew Ng, Kian Katanforoosh, and Younes Bensouda Mourri

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.

Enroll now

Or subscribe to Coursera Plus

And get unlimited access to Coursera

Three deals to help you save

We found three deals and offers that may be relevant to this course.

Save money when you learn. All coupon codes, vouchers, and discounts are applied automatically unless otherwise noted.

Valid until December 12

Annual Subscription Savings

Unlock programs from Google, Microsoft, and IBM and join 77% of learners who reported positive career outcomes.

Only $239!

Valid for a limited time only

Future-proof your career

Access O'Reilly books, live events, courses, and more. Save with an annual subscription.

Take

15%

off

What's inside

Syllabus

Foundations of Convolutional Neural Networks

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

Deep Convolutional Models: Case Studies

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.

Object Detection

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

Special Applications: Face recognition & Neural Style Transfer

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!

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Appropriate for learners with a background in computer vision

Builds on foundational computer vision knowledge and strengthens intermediate learners' existing foundation

Covers object detection, face recognition, and neural style transfer, offering practical applications and industry-relevant skills

Examines recent advancements and case studies in deep CNNs, exposing learners to innovative techniques

Offers opportunities for hands-on implementation of CNNs, providing practical experience

Taught by recognized instructors in the field of computer vision, Andrew Ng and Younes Bensouda Mourri

Save this course

Save Convolutional Neural Networks to your list so you can find it easily later:

Save

Reviews summary

Convolutional neural networks

The course covers a comprehensive overview of Convolutional Neural Networks (CNNs), with a focus on the fundamental principles and practical applications of CNNs in computer vision tasks. It begins with the basics of CNNs, including convolutional layers, pooling layers, and activation functions. The course then explores advanced CNN architectures, such as Residual Networks (ResNets) and Inception Networks, and their applications in image classification, object detection, and neural style transfer. Throughout the course, students gain hands-on experience through programming assignments and quizzes, reinforcing their understanding of CNNs and their practical implementation. The course is designed for aspiring deep learning practitioners and students with a basic understanding of machine learning and deep learning concepts. It provides a solid foundation for further study and research in computer vision and deep learning.

The course offers a good balance between theoretical explanations and practical implementation. The programming assignments and quizzes help students apply their knowledge and reinforce their understanding of CNNs.

"The course covers a comprehensive overview of Convolutional Neural Networks (CNNs), with a focus on the fundamental principles and practical applications of CNNs in computer vision tasks."

"Throughout the course, students gain hands-on experience through programming assignments and quizzes, reinforcing their understanding of CNNs and their practical implementation."

The course provides a solid foundation in the fundamental principles of CNNs, including convolutional layers, pooling layers, and activation functions. This lays the groundwork for understanding more advanced CNN architectures and their applications.

"It begins with the basics of CNNs, including convolutional layers, pooling layers, and activation functions."

The course explores advanced CNN architectures, such as Residual Networks (ResNets) and Inception Networks. This exposure to cutting-edge techniques provides students with a glimpse into the latest developments in computer vision and deep learning.

"The course then explores advanced CNN architectures, such as Residual Networks (ResNets) and Inception Networks, and their applications in image classification, object detection, and neural style transfer."

The course showcases the practical applications of CNNs in a variety of computer vision tasks, including image classification, object detection, and neural style transfer. This demonstrates the wide-ranging capabilities of CNNs and their potential impact in various domains.

The course material is presented in a clear and engaging manner. Andrew Ng's teaching style makes complex concepts accessible and easy to understand, even for students with limited prior knowledge in deep learning.

The course is taught by Andrew Ng, a renowned expert in deep learning and artificial intelligence. His knowledge and experience add credibility to the course material and provide students with valuable insights into the field.

While the programming assignments provide hands-on experience, they are challenging and require a good understanding of the material. This can be a drawback for beginners or students who may not have a strong programming background.

Some students have reported that certain course materials, such as links to documentation and code examples, may be outdated. This can be frustrating and may require students to seek additional resources to complete the assignments.

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Convolutional Neural Networks with these activities:

Review the book 'Deep Learning with Python'

Show steps

Gain a deeper understanding of the concepts covered in the course by reading a book on the subject.

View Deep learning v jazyku Python - 2., rozšířené... on Amazon

Show steps

Purchase or borrow the book.
Read the book and take notes on the key concepts.
Complete the exercises and assignments in the book.

Watch a tutorial on convolutional neural networks

Show steps

Get a quick overview of the basics of CNNs before diving into the course material.

Browse courses on Convolutional Neural Networks

Show steps

Find a tutorial on YouTube or another online platform.
Watch the tutorial and take notes on the key concepts.

Implement a simple CNN in Python

Show steps

Solidify your understanding of CNNs by implementing one from scratch.

Browse courses on Python

Show steps

Set up a Python environment with the necessary libraries.
Create a dataset of images for training and testing.
Design and implement a CNN architecture.
Train and evaluate the CNN on the dataset.

One other activity

Expand to see all activities and additional details

Show all four activities

Write a blog post about a CNN project you worked on

Show steps

Showcase your knowledge and understanding of CNNs by creating a project and sharing it with others.

Show steps

Identify a problem or challenge that can be solved using a CNN.
Design and implement a CNN-based solution.
Write a blog post describing your project, the problem it solves, and the results you achieved.

Career center

Learners who complete Convolutional Neural Networks will develop knowledge and skills that may be useful to these careers:

Computer Vision Engineer

A Convolutional Neural Networks course provides a good foundation towards becoming a successful Computer Vision Engineer by providing the fundamental knowledge and tools needed to work with images and videos. Those who wish to enter the field of Computer Vision Engineering may find this course particularly relevant as it covers techniques commonly used in the field, such as object detection and face recognition.

See salaries and explore the career path for Computer Vision Engineer

Data Scientist

A Convolutional Neural Networks course is highly relevant for those aspiring to become Data Scientists. It provides a comprehensive understanding of deep learning techniques specifically designed for analyzing and interpreting images and videos, which is becoming increasingly important in various domains, such as medical imaging, autonomous driving, and security.

See salaries and explore the career path for Data Scientist

Machine Learning Engineer

A Convolutional Neural Networks course is beneficial for Machine Learning Engineers as it provides expertise in designing, developing, and implementing deep learning models for computer vision tasks. The course covers advanced techniques like transfer learning and object detection, equipping Machine Learning Engineers with specialized knowledge for working on complex image and video-related projects.

See salaries and explore the career path for Machine Learning Engineer

Software Engineer

The skills learned in a Convolutional Neural Networks course, such as building and training deep neural networks, can be applied by Software Engineers who work on developing and maintaining software for various applications. This course offers a solid foundation for Software Engineers who want to specialize in deep learning and computer vision.

See salaries and explore the career path for Software Engineer

Research Scientist

For those pursuing careers as Research Scientists in the field of computer vision or deep learning, a Convolutional Neural Networks course is highly recommended. It offers a deep dive into the latest developments and research advancements in this domain, providing a solid foundation for conducting cutting-edge research and contributing to the field.

See salaries and explore the career path for Research Scientist

Product Manager

Product Managers who work on developing computer vision-based products can benefit from a Convolutional Neural Networks course. It provides a technical understanding of the underlying algorithms and techniques, enabling them to make informed decisions, prioritize features, and effectively communicate with engineering teams.

See salaries and explore the career path for Product Manager

Data Analyst

A Convolutional Neural Networks course can be useful for Data Analysts who work with image or video data. It provides specialized knowledge in deep learning techniques tailored for analyzing and extracting insights from visual data, enhancing their ability to interpret and communicate data-driven insights.

See salaries and explore the career path for Data Analyst

Business Analyst

While a Convolutional Neural Networks course is not directly related to the role of a Business Analyst, it may provide valuable knowledge for those involved in projects related to computer vision or image analysis. Understanding the capabilities and limitations of these technologies can aid in identifying business opportunities and developing effective strategies.

See salaries and explore the career path for Business Analyst

Project Manager

For Project Managers working on computer vision or deep learning projects, a Convolutional Neural Networks course can be helpful. It provides a technical foundation to understand the project's scope, timelines, and deliverables, enabling effective planning, resource allocation, and risk management.

See salaries and explore the career path for Project Manager

Technical Writer

Technical Writers who specialize in documenting deep learning or computer vision technologies can benefit from a Convolutional Neural Networks course. It provides in-depth knowledge of the subject matter, enabling them to create accurate, clear, and comprehensive technical documentation for various audiences.

See salaries and explore the career path for Technical Writer

Sales Engineer

Sales Engineers who work with clients in the computer vision or deep learning industry may find a Convolutional Neural Networks course beneficial. It provides technical expertise to understand the products and solutions being sold, enabling them to effectively communicate their value and benefits to potential customers.

See salaries and explore the career path for Sales Engineer

IT Consultant

IT Consultants who specialize in computer vision or deep learning can enhance their knowledge and skills by taking a Convolutional Neural Networks course. It provides a deep understanding of the latest advancements and best practices in the field, enabling them to provide expert advice and guidance to clients.

See salaries and explore the career path for IT Consultant

UX Designer

UX Designers who work on projects involving computer vision or image-based interfaces may find a Convolutional Neural Networks course helpful. It provides insights into the capabilities and limitations of these technologies, enabling them to design user experiences that leverage visual data effectively.

See salaries and explore the career path for UX Designer

Quantitative Analyst

Quantitative Analysts who work with visual data or apply deep learning techniques to financial analysis may benefit from a Convolutional Neural Networks course. It provides specialized knowledge in image analysis and deep learning algorithms, enhancing their ability to develop and implement data-driven models.

See salaries and explore the career path for Quantitative Analyst

Marketing Manager

Marketing Managers who work on campaigns or products related to computer vision or deep learning can gain insights from a Convolutional Neural Networks course. It provides an understanding of the technology's capabilities and potential applications, enabling them to develop effective marketing strategies and communicate the value of these technologies to target audiences.

See salaries and explore the career path for Marketing Manager

Reading list

We've selected 14 books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Convolutional Neural Networks.

Deep Learning

Save

Comprehensive resource on deep learning and provides a solid foundation for understanding the theoretical underpinnings of convolutional neural networks.

Convolutional Neural Networks

Three deals to help you save

What's inside

Syllabus

Good to know

Save this course

Reviews summary

Convolutional neural networks

Activities

Career center

Reading list

Share

Similar courses