About this course: 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. You will: - Understand how to build a convolutional neural network, including recent variations such as residual networks. - Know how to apply convolutional networks to visual detection and recognition tasks. - Know to use neural style transfer to generate art. - Be able to apply these algorithms to a variety of image, video, and other 2D or 3D data. This is the fourth course of the Deep Learning Specialization.
Who is this class for: - Learners that took the first two courses of the specialization. The third course is recommended. - Anyone that already has a solid understanding of densely connected neural networks, and wants to learn convolutional neural networks or work with image data.
Taught by: Andrew Ng, Co-founder, Coursera; Adjunct Professor, Stanford University; formerly head of Baidu AI Group/Google Brain
Taught by: Head Teaching Assistant - Kian Katanforoosh, Lecturer of Computer Science at Stanford University, deeplearning.ai, Ecole CentraleSupelec
Taught by: Teaching Assistant - Younes Bensouda Mourri, Mathematical & Computational Sciences, Stanford University, deeplearning.ai
| Basic Info | Course 4 of 5 in the Deep Learning Specialization |
| Level | Intermediate |
| Commitment | 4 weeks of study, 4-5 hours/week |
| Language | English, Subtitles: Chinese (Traditional), Korean |
| Hardware Req | None currently, unless you'd like to download Jupyter Notebooks locally for offline work. |
| How To Pass | Pass all graded assignments to complete the course. |
| User Ratings |
- Video: Edge Detection Example
- Video: More Edge Detection
- Video: Padding
- Video: Strided Convolutions
- Video: Convolutions Over Volume
- Video: One Layer of a Convolutional Network
- Video: Simple Convolutional Network Example
- Video: Pooling Layers
- Video: CNN Example
- Video: Why Convolutions?
- Notebook: Convolutional Model: step by step
- Notebook: Convolutional Model: application
- Video: Yann LeCun Interview
- Video: Classic Networks
- Video: ResNets
- Video: Why ResNets Work
- Video: Networks in Networks and 1x1 Convolutions
- Video: Inception Network Motivation
- Video: Inception Network
- Video: Using Open-Source Implementation
- Video: Transfer Learning
- Video: Data Augmentation
- Video: State of Computer Vision
- Notebook: Keras Tutorial - The Happy House (not graded)
- Notebook: Residual Networks
- Video: Landmark Detection
- Video: Object Detection
- Video: Convolutional Implementation of Sliding Windows
- Video: Bounding Box Predictions
- Video: Intersection Over Union
- Video: Non-max Suppression
- Video: Anchor Boxes
- Video: YOLO Algorithm
- Video: (Optional) Region Proposals
- Notebook: Car detection with YOLOv2
- Video: One Shot Learning
- Video: Siamese Network
- Video: Triplet Loss
- Video: Face Verification and Binary Classification
- Video: What is neural style transfer?
- Video: What are deep ConvNets learning?
- Video: Cost Function
- Video: Content Cost Function
- Video: Style Cost Function
- Video: 1D and 3D Generalizations
- Notebook: Art generation with Neural Style Transfer
- Notebook: Face Recognition for the Happy House
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
| Purchase Course | |
|---|---|
| Access to course materials | Available |
| Access to graded materials | Available |
| Receive a final grade | Available |
| Earn a shareable Course Certificate | Available |
Definitely helps focus your interest.
I'm sure many people take this course and absolutely love it. I didn't have that experience. Don't get me wrong, it's thorough, taught by an expert who, by the time you get to this course you'll trust unconditionally, and there's plenty of guidance from people who've taken the course before. I'm sure you won't run into any problem that someone else hasn't had before. Anyway, I did get something valuable from the course. I learned I have absolutely no interest in computer vision / image recognition. That made it very difficult to persevere and finish 4 weeks of this stuff, but it is a valuable insight and it lets me continue to course 5.
The Way Prof. Andrew explains things, taking us from simple stuff to the complex conclusions by ourselves making it so much easier and convincing!
The course content was great and assignments were fun, I like that in the end of each assignment there is always a cell that's like a "playing ground" allowing you try and test the models you created.
Excellent & Simple!!
very good! I love Ag so much.