11 Best + Free Deep Learning Courses & Certification [UPDATED]
As featured on Harvard EDU, Stackify and Inc - CourseDuck identifies and rates the Best Deep Learning Courses, Tutorials, Providers and Certifications, based on 12,000+ student reviews, public mentions, recommendations, ratings and polling 5,000+ highly active StackOverFlow members. Learn more
- 1. CS231n: Convolutional Neural Networks for Visual Recognition [Stanford University] - Best Free Course
- 2. Practical Deep Learning for Coders, v3 [fast.ai] - Best Practical Course
- 3. Deep Learning: A Crash Course [YouTube] - Best Crash Course
- 4. Complete Guide to TensorFlow for Deep Learning with Python [Udemy] - Best Paid Course
- 5. MIT Deep Learning for Self-Driving Cars [YouTube] - Best NEW Course
- 6. Deep Learning by MIT Press [MIT Press] - Best Text Based Course
- 7. Neural Networks and Deep Learning [Coursera] - Best Advanced Course
- 8. Deep Learning with PyTorch [Manning Publications]
- 9. Deep Learning Nanodegree [Udacity]
- 10. Deep Learning and the Game of Go [Manning Publications]
Deep Learning A-Z: Hands-On Artificial Neural Networks (2019)
- Course is a great first look at neural networks.
- Course takes time to develop an intuitive understanding of neural networks to broaden students approaches to design.
- Even students with limited coding backgrounds have succeeded in this course.
- If you arent good at Python, you will have to become good at it, and on your own time.
- Course leaves a large number of AI strategies and philosophies off the table.
- Course is math-heavy and that can prove a barrier for some students.
CS231n: Convolutional Neural Networks for Visual Recognition (2017)
- This is an elite class taught by an elite university. Completing this course denotes high-level proficiency in neural network design and implementation.
- Course is available for audit and sit-in.
- This is an active college course and comes with the professor access that entails.
- This is an advanced class and not readily accessible. Students need to know calculus and linear algebra in addition to multiple programming languages.
- Course is just plain hard.
- Course access is prioritized for the Stanford community.
Practical Deep Learning for Coders, v3 (2019)
- Experienced instructor that provides easy to understand explanations and teaches you "how-to" instead of "why".
- Top-down learning approach perfect for students that want to apply Machine Learning fast.
- Great community of fellow-learners to help you along the course.
- This course uses fastai library that can be too difficult for beginners.
- To understand the theory befind the course, further readings and additional information are necessary.
Deep Learning: A Crash Course (2018)
- Video has a sense of humor which is great for de-stressing a long session on deep topics.
- Course does a great job of covering legitimate applications, helping students to understand where to take their knowledge for future development.
- Despite the video length, the course is surprisingly succinct.
- One video is not enough to thoroughly cover deep learning. Its a big topic.
- Course is severely lacking in supplemental information.
- Course is really just a recording of lectures, minus the resources used in the lectures.
Complete Guide to TensorFlow for Deep Learning with Python (2017)
MIT Deep Learning for Self-Driving Cars (2019)
- The instructor is a researcher from one of the most prestigious universities in the world.
- The concepts are presented in a clear and straight-forward manner.
- Real-world examples to help you understand how to apply the theory behind Deep Learning.
- Too many topics covered in one tutorial, only scratches the surface of each.
- Lacks interactivity which can be inconvenient for learners to easily comprehend key concepts.
Deep Learning by MIT Press (2016)
- Covers the latest developments of Deep Learning.
- Clear and sophisticated presentation.
- Considered as "the Bible" of Machine Learning.
- Written by one of the most respected AI researchers.
- Perfect as a reference for further learning and research.
- The book is written in a high-level academic manner. Will be difficult to understand for some.
- Not recommended for students that prefer step-by-step tutorials.
Neural Networks and Deep Learning (2017)
- Offered by deeplearning.ai, a well known provider of a world-class AI education.
- Taught in Python and Jupyter Notebook.
- Good introduction to how to build and implement neural networks.
- Easy to understand lectures with a mix of theory and practical application.
- Useful tips and insights into Deep Learning.
- Pre-written code in assignments.
- Repetitive content.