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

Deep Learning

An introduction to the field of deep learning, including neural networks, convolutional neural networks, recurrent neural networks, transformers, generative models, neural network compression and transfer learning. This course will benefit students’ careers as a machine learning engineer or data scientist.

Enroll now

Or subscribe to Coursera Plus

And get unlimited access to Coursera

Two deals to help you save

Save money when you learn. Here are two deals and offers that may be relevant to this course.

All coupon codes, vouchers, and discounts are applied automatically unless otherwise noted.

Valid until December 2

Annual Subscription

Invest in your career growth and save. Start your annual subscription to Coursera Plus and access 10,000+ programs.

Valid until March 12, 2027

Save 40% Off 3 Months

Access thousands of top-rated learning programs with a Coursera Plus monthly subscription and take 40% off 3 months for a limited time.

What's inside

Syllabus

Module 1: Neural Networks

Welcome to Deep Learning! In module 1, we will give an introduction to deep learning. Deep learning is a branch of machine learning which is based on artificial neural networks. It is capable of learning complex patterns and relationships within data. Particularly, we will discuss feed-forward deep neural network. We will also discuss backpropagation – the way to optimize deep neural networks.

Traffic lights

Read about what's good

what should give you pause

and possible dealbreakers

Teaches deep learning and machine learning methods used for object recognition

Instructed by experts in deep learning and machine learning

Covers foundational material in deep learning, including foundational and advanced topics

Suitable for learners with no prior knowledge in deep learning

Provides practical, applicable knowledge and skills

May require access to additional resources, which could incur costs

Save this course

Create your own learning path. Save this course to your list so you can find it easily later.

Save

Reviews summary

Deep learning: practical and comprehensive foundation

According to learners, this 'Deep Learning' course provides a highly practical and comprehensive introduction, proving especially beneficial for aspiring machine learning engineers and data scientists. Many students highlight the instructor's exceptional clarity in explaining complex topics such as Transformers and Generative Adversarial Networks (GANs). The course is frequently praised for its up-to-date content and numerous hands-on coding exercises, which significantly enhance understanding and real-world application. While largely providing a strong foundational understanding, some students noted that certain areas, like optimization methods or advanced model implementation, could benefit from greater mathematical rigor or more in-depth practical guidance, occasionally prompting the need for supplementary study.

Course's mathematical depth may not satisfy all learners.

"I found the lectures to be quite superficial in certain areas, particularly when dealing with the mathematical underpinnings. As someone with a strong math background, I was hoping for more rigor."

"The course provides a strong foundation, making complex topics accessible even for someone new to the field, but might lack the deep mathematical explanations some experienced learners seek."

Offers valuable coding exercises for applying theoretical knowledge.

"The hands-on coding exercises were invaluable, especially the ones involving PyTorch."

"An excellent course for anyone looking to understand deep learning from a practical standpoint. The focus on applications and real-world scenarios was a major plus for me."

"I found this course incredibly useful for leveling up my deep learning skills. The content is up-to-date and practical."

Covers a wide range of current and essential deep learning topics.

"The course content is very current and relevant to today's ML landscape."

"The course covers a wide range of cutting-edge topics, from foundational neural networks to modern generative models and even model compression."

"The coverage of transformers and diffusion models is a huge plus. The content is up-to-date and practical."

The instructor excels at simplifying complex deep learning concepts.

"The instructor explains complex topics like Transformers and GANs with incredible clarity..."

"The professor's enthusiasm shines through, and their ability to simplify difficult concepts is remarkable."

"Their explanations of backpropagation and LSTMs were the clearest I've encountered."

Forum discussions could be more active for timely support.

"My only minor complaint is that the forum discussions were not very active, making it harder to get questions answered quickly."

"I felt that the discussion on practical tips (Module 3) could have been expanded. More real-world scenarios and common pitfalls would be beneficial."

Some topics may require external resources for deeper understanding.

"My only minor critique is that some explanations, especially for optimization methods, could have been a bit more in-depth. I had to look up external resources for a complete understanding."

"I found myself needing to supplement with other materials to fully grasp the nuances."

"Good overview, but not enough depth. I needed more guidance on implementing complex models from scratch."

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 Deep Learning with these activities:

Review 'Deep Learning' by Yoshua Bengio

Show steps

Build a strong foundation by reading the seminal textbook on Deep Learning

View Deep Learning on Amazon

Show steps

Read and summarize Chapter 1: Introduction
Read and complete exercises for Chapter 2: Feedforward Neural Networks
Read and summarize Chapter 3: Convolutional Neural Networks

Solve practice problems on backpropagation

Show steps

Strengthen your foundation in how neural networks learn

Browse courses on Backpropagation

Show steps

Solve 10 practice problems on backpropagation
Debug your code or approach with a peer or TA

Attend weekly study group for discussion and Q&A

Show steps

Deepen your understanding through peer collaboration and exchange of ideas

Browse courses on Neural Networks

Show steps

Regularly attend study group sessions
Actively participate in discussions and ask questions
Prepare questions or topics to present to the group

Five other activities

Expand to see all activities and additional details

Show all eight activities

Review 'Recurrent Neural Networks' by Alex Graves

Show steps

Expand your knowledge of RNNs and their applications

View Supervised Sequence Labelling with Recurrent... on Amazon

Show steps

Read and summarize Chapter 1: Introduction to RNNs
Read and complete exercises for Chapter 2: LSTM Networks
Read and summarize Chapter 3: Applications of RNNs

Build a neural network model for image classification

Show steps

Gain practical experience in applying neural networks to real-world problems

Browse courses on Neural Networks

Show steps

Collect or find a dataset of images
Build a neural network model using a framework like PyTorch or TensorFlow
Train and evaluate your model
Present your results to peers or instructors for feedback

Follow a tutorial on Generative Adversarial Networks

Show steps

Gain exposure to advanced and emerging techniques in Deep Learning

Browse courses on Generative Adversarial Networks

Show steps

Find a comprehensive tutorial on GANs
Follow the tutorial step-by-step and implement your own GAN model
Share your results with the community or apply them to a project

Contribute to an open-source deep learning library

Show steps

Gain practical experience and network with the deep learning community

Browse courses on Deep Learning

Show steps

Identify a suitable open-source project
Fork the project and make a contribution
Submit a pull request and engage with the project maintainers

Start a personal project on neural network compression

Show steps

Enhance your understanding of advanced topics and develop your problem-solving abilities

Browse courses on Deep Learning

Show steps

Define the scope and goals of your project
Research existing techniques and algorithms
Implement and test your own compression methods
Evaluate and compare your results against baselines

Career center

Learners who complete Deep Learning will develop knowledge and skills that may be useful to these careers:

Reading list

We've selected 43 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 Deep Learning.

Deep Learning

Save

Provides a comprehensive overview of deep learning, including convolutional neural networks. It is written by three leading researchers in the field and is suitable for both beginners and experienced practitioners.

Deep Learning (Adaptive Computation and Machine...

Hardcover

$$$

Deep Learning (Adaptive Computation and Machine...

Kindle Edition

$$$

Natural Language Processing with Transformers,...

Save

Co-authored by creators of the Hugging Face ecosystem, the revised edition serves as the definitive practitioner manual for training, fine-tuning, and deploying encoder-decoder and decoder-only transformers. Readers dissect multi-head self-attention, tokenization pipelines, and model quantization through production PyTorch code.

Deep Learning

Two deals to help you save

What's inside

Syllabus

Traffic lights

Save this course

Reviews summary

Deep learning: practical and comprehensive foundation

Activities

Career center

Reading list

Share

Similar courses

Coursera Buyer Protection & Guarantee

7-Day Free Trial & Free Audit

14-Day Refund Guarantee

Verified Academic & Industry Partner