You might be wondering if this is the right program for you, worried that you don’t have the time, or afraid that you won’t be able to keep up?
We understand that it can be daunting to start something new.
Professional CertificateIntermediate127 hours 29 mins
Deep Learning Specialization
Instructor: Andrew Ng
Enroll Now
Also available on Coursera
- Intermediate
- 127 hours 29 mins
- 194 Video Lessons
- 1 Code Examples
- Instructor: Andrew Ng
The Deep Learning Specialization
Has clear, concise modules that allow for self-paced learning.
Introduces practical techniques to help you get started on your AI projects and develop an industry portfolio.
Has a 1 million-strong learner community that will support and guide you.
Breaks down foundational concepts into easy-to-understand lectures and engaging assignments.
Is up-to-date with the leading-edge in machine learning.
Is rated 4.9 out of 5 by 120K+ learners and is among the most popular data science programs on Coursera
Learner reviews
Sharob Sinha
“After completing the Deep Learning Specialization, I got two promotions and an award and was able to work with the R&D team at work. I also got the opportunity to teach undergrad engineering students. These experiences, starting with DLS, have molded my career.”
Jose Ramirez
“I decided to try to understand this thing called AI that everyone was talking about and ended up doing the Deep Learning Specialization. I truly believe that this program should be given to senior students at universities as they’d get a valuable picture.”
Wonjin Kim
“The Deep Learning Specialization helped me build the fundamental knowledge as well as practical applications of deep learning. I think the Deep Learning Specialization is a great starting point if someone wants to get into the field.”
Ludovic Alarie-Vezina
“The introductions to Convolutional Neural Networks, Yolo, NLP, among others, really helped me hit the ground running when I got on the job market. As I developed more experience, I transitioned from being a multi-project consultant to being the lead scientist of a startup.”
Sayak Pal
“When my role as a software engineer at a big company started feeling claustrophobic, I quit without having another job in hand and enrolled in the Deep Learning Specialization. This fueled my knowledge appetite, and today, I work as a Machine Learning Engineer at Carted.”
Samuel Cahyawijaya
“After the Deep Learning Specialization, I realized that deep learning isn’t just for those with a math background and decided to become a machine learning engineer. The knowledge I’d gained helped me transition from analytics to an AI researcher role in an NLP research lab.”
Krystof Chotas
“The skills I acquired after completing the Deep Learning Specialization helped me get a better job. The insights it provided into the subject matter enabled me to develop new and innovative solutions to problems at work.”
Jora De Jong
“The Deep Learning Specialization allowed me to understand diverse approaches to solve problems and helped by providing deeper insight into the field. After completing the program, I understood foundational principles better and was able to feel much more in control.”
Jan Zawadzki – Deep Learning Specialization
“Within a few minutes and a couple slides, I had the feeling that I could learn any concept. I felt like a superhero after this course. I didn’t know much about deep learning before, but I felt like I gained a strong foothold afterward.”
Kritika Jalan – Deep Learning Specialization
“The whole specialization was like a one-stop-shop for me to decode neural networks and understand the math and logic behind every variation of it. I can say neural networks are less of a black box for a lot of us after taking the course.”
Chris Morrow – Deep Learning Specialization
“During my Amazon interview, I was able to describe, in detail, how a prediction model works, how to select the data, how to train the model, and the use cases in which this model could add value to the customer.”
Don’t Let the Machine Learning Revolution Pass You By
#BeADeepLearner with the
Deep Learning Specialization.
Instructor
Skills you will gain
- Tensorflow
- Artificial Neural Networks
- Convolutional Neural Networks
- Recurrent Neural Networks
- Transformers
- Python Programming
- Deep Learning
- Backpropagation
- Optimization
- Hyperparameter Tuning
- Machine Learning
- Transfer Learning
- Multi-Task Learning
- Object Detection and Segmentation
- Facial Recognition System
- Gated Recurrent Unit (GRU)
- Long Short Term Memory (LSTM)
- Attention Models
- Natural Language Processing
Course Outline
Neural Networks and Deep Learning
This course is part of Deep Learning Specialization
Week 1: Introduction to Deep Learning
Welcome to the Deep Learning Specialization
Introduction to Deep Learning
Lecture Notes (Optional)
Heroes of Deep Learning (Optional)
Week 2: Neural Networks Basics
- Binary ClassificationVideo・8 mins
- Logistic RegressionVideo・5 mins
- Logistic Regression Cost FunctionVideo・8 mins
- Gradient DescentVideo・11 mins
- DerivativesVideo・7 mins
- More Derivative ExamplesVideo・10 mins
- Computation GraphVideo・3 mins
- Derivatives with a Computation GraphVideo・14 mins
- Logistic Regression Gradient DescentVideo・6 mins
- Gradient Descent on m ExamplesVideo・8 mins
- Derivation of DL/dz (Optional)Reading・10 mins
- VectorizationVideo・8 mins
- More Vectorization ExamplesVideo・6 mins
- Vectorizing Logistic RegressionVideo・7 mins
- Vectorizing Logistic Regression's Gradient OutputVideo・9 mins
- Broadcasting in PythonVideo・11 mins
- A Note on Python/Numpy VectorsVideo・6 mins
- Quick tour of Jupyter/iPython NotebooksVideo・3 mins
- Explanation of Logistic Regression Cost Function (Optional)Video・7 mins
- Deep Learning Honor CodeReading・2 mins
- Programming Assignment FAQReading・10 mins
- (Optional) Downloading your Notebook, Downloading your Workspace and Refreshing your WorkspaceReading・5 mins
- Python Basics with Numpy
Graded・Code Assignment
・1 hour - Logistic Regression with a Neural Network Mindset
Graded・Code Assignment
・3 hours
Logistic Regression as a Neural Network
Python and Vectorization
Lecture Notes (Optional)
Programming Assignments
Heroes of Deep Learning (Optional)
Week 3: Shallow Neural Networks
- Neural Networks OverviewVideo・4 mins
- Neural Network RepresentationVideo・5 mins
- Computing a Neural Network's OutputVideo・9 mins
- Vectorizing Across Multiple ExamplesVideo・9 mins
- Explanation for Vectorized ImplementationVideo・7 mins
- Activation FunctionsVideo・10 mins
- Why do you need Non-Linear Activation Functions?Video・5 mins
- Derivatives of Activation FunctionsVideo・7 mins
- Gradient Descent for Neural NetworksVideo・9 mins
- Backpropagation Intuition (Optional)Video・15 mins
- Random InitializationVideo・7 mins
Shallow Neural Network
Lecture Notes (Optional)
Programming Assignment
Heroes of Deep Learning (Optional)
Week 4: Deep Neural Networks
- Deep L-layer Neural NetworkVideo・5 mins
- Forward Propagation in a Deep NetworkVideo・7 mins
- Getting your Matrix Dimensions RightVideo・11 mins
- Why Deep Representations?Video・10 mins
- Building Blocks of Deep Neural NetworksVideo・8 mins
- Forward and Backward PropagationVideo・10 mins
- Optional Reading: Feedforward Neural Networks in DepthReading・10 mins
- Parameters vs HyperparametersVideo・7 mins
- Clarification For: What does this have to do with the brain?Reading・1 min
- What does this have to do with the brain?Video・3 mins
Deep Neural Network
Lecture Notes (Optional)
End of access to Lab Notebooks
Programming Assignments
References & Acknowledgments
Course Slides
You can download the annotated version of the course slides below.
*Note: The slides might not reflect the latest course video slides. Please refer to the lecture videos for the most up-to-date information. We encourage you to make your own notes.Frequently Asked Questions
What is Deep Learning? Why is it relevant?
Deep Learning is a subset of machine learning where artificial neural networks, algorithms based on the structure and functioning of the human brain, learn from large amounts of data to create patterns for decision-making. Neural networks with various (deep) layers enable learning through performing tasks repeatedly and tweaking them a little to improve the outcome.
Over the last few years, the availability of computing power and the amount of data being generated have led to an increase in deep learning capabilities. Today, deep learning engineers are highly sought after, and deep learning has become one of the most in-demand technical skills as it provides you with the toolbox to build robust AI systems that just weren’t possible a few years ago. Mastering deep learning opens up numerous career opportunities.
What is the Deep Learning Specialization about?
The Deep Learning Specialization is a 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.
In this Specialization, you will build and train neural network architectures such as Convolutional Neural Networks, Recurrent Neural Networks, LSTMs, Transformers, and learn how to make them better with strategies such as Dropout, BatchNorm, Xavier/He initialization, and more. Get ready to master theoretical concepts and their industry applications using Python and TensorFlow and tackle real-world cases such as speech recognition, music synthesis, chatbots, machine translation, natural language processing, and more.
AI is transforming many industries. The Deep Learning Specialization provides a pathway for you to take the definitive step in the world of AI by helping you gain the knowledge and skills to level up your career. Along the way, you will also get career advice from deep learning experts from industry and academia.
What will I be able to do after completing the Deep Learning Specialization?
By the end of the Deep Learning Specialization, you will be able to:
- Build and train deep neural networks, implement vectorized neural networks, identify architecture parameters, and apply DL to your applications.
- Use best practices to train and develop test sets and analyze bias/variance for building DL applications, use standard NN techniques, apply optimization algorithms, and implement a neural network in TensorFlow.
- Use strategies for reducing errors in ML systems, understand complex ML settings, and apply end-to-end, transfer, and multi-task learning.
- Build a Convolutional Neural Network, apply it to visual detection and recognition tasks, use neural style transfer to generate art, and apply these algorithms to image, video, and other 2D/3D data.
- Build and train Recurrent Neural Networks and its variants (GRUs, LSTMs), apply RNNs to character-level language modeling, work with NLP and Word Embeddings, and use HuggingFace tokenizers and transformers to perform Named Entity Recognition and Question Answering.
What background knowledge is necessary for the Deep Learning Specialization?
Expected:
- Learners should have intermediate Python experience (e.g., basic programming skills, understanding of for loops, if/else statements, data structures such as lists and dictionaries).
Recommended:
- Learners should have a basic knowledge of linear algebra (matrix-vector operations and notation).
- Learners should have an understanding of machine learning concepts (how to represent data, what an ML model does, etc.)
Who is the Deep Learning Specialization for?
The Deep Learning Specialization is for early-career software engineers or technical professionals looking to master fundamental concepts and gain practical machine learning and deep learning skills.
How long does it take to complete the Deep Learning Specialization?
The Deep Learning Specialization consists of five courses. At the rate of 5 hours a week, it typically takes 5 weeks to complete each course except course 3, which takes about 4 weeks.
Who is the Deep Learning Specialization by?
The Deep Learning Specialization has been created by Andrew Ng, Kian Katanforoosh, and Younes Bensouda Mourri.
Andrew Ng is Founder of DeepLearning.AI, General Partner at AI Fund, Chairman and Co-Founder of Coursera, and an Adjunct Professor at Stanford University. As a pioneer in machine learning and online education, Dr. Ng has changed countless lives through his work in AI, authoring or co-authoring over 100 research papers in machine learning, robotics, and related fields. Previously, he was chief scientist at Baidu, the founding lead of the Google Brain team, and the co-founder of Coursera – the world’s largest MOOC platform.
Kian Katanforoosh is the co-founder and CEO of Workera and a lecturer in the Computer Science department at Stanford University. Workera allows data scientists, machine learning engineers, and software engineers to assess their skills against industry standards and receive a personalized learning path. Kian is also the recipient of Stanford’s Walter J. Gores award (Stanford’s highest teaching award) and the Centennial Award for Excellence in teaching.
Younes Bensouda Mourri completed his Bachelor’s in Applied Mathematics and Computer Science and Master’s in Statistics from Stanford University. Younes helped create 3 AI courses at Stanford – Applied Machine Learning, Deep Learning, and Teaching AI – and taught two of them for a few years.
The Deep Learning Specialization was updated in April 2021. What is different in the new version?
- All existing assignments and autograders have been refactored and updated to TensorFlow 2 across Courses 1, 2, 4, and 5.
- Three new network architectures are presented with new lectures and programming assignments:
- Course 4 includes MobileNet (transfer learning) and U-Net (semantic segmentation).
- Course 5, once updated, will include Transformers (Network Architecture, Named Entity Recognition, Question Answering).
- For a detailed list of changes, please check out the DLS Changelog.
I’m currently enrolled in one or more courses in the Deep Learning Specialization. What does this mean for me?
- Your certificates will carry over for any courses you’ve already completed.
- If your subscription is currently active, you can access the updated labs and submit assignments without paying for the month again.
- If you go to the Specialization, you will see the original version of the lecture videos and assignments. You can complete the original version if so desired (this is not recommended).
- If you would like to update to the new material, reset your deadlines. If you’re in the middle of a course, you will lose your notebook work when you reset your deadlines. Please save your work by downloading your existing notebooks before switching to the new version.
- If you do not see the option to reset deadlines, contact Coursera via the Learner Help Center.
Is this a standalone course or a Specialization?
The Deep Learning Specialization is made up of 5 courses.
Do I need to take the courses in a specific order?
We recommend taking the courses in the prescribed order for a logical and thorough learning experience. Course 3 can also be taken as a standalone course.
How much does the Specialization cost?
The DeepLearning.AI Pro membership costs $25/mo billed annually and $30/mo billed monthly.
More pricing details are available on the membership page.
Important details:
- All prices are listed in USD
- Payments are processed securely via Stripe
- Taxes may apply depending on your location
What Learners Are Saying
