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:Â Â Andrew Ng, Co-founder, Coursera; Adjunct Professor, Stanford University; formerly head of Baidu AI Group/Google Brain
Taught by:Â Â Head Teaching Assistant - Kian Katanforoosh, Adjunct Lecturer at Stanford University, deeplearning.ai, Ecole Centrale Paris
Taught by:Â Â 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 |
| 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 |
From the course, we can learn the details of CNN and how it grew. Maybe someday we can apply the great ideas from CNN to other problems. I learned much from this course.
Awesome!
Great lectures and exercises but the leave-behind study materials (lecture slides and notebooks) could be a little more helpful, and the frequent server disconnects have forced me to do most of the programming work offline.
You will get deeper understanding how CNN works after you finish this course. Great course!