Convolutional Neural Networks
deeplearning.ai and Stanford University via Coursera
Overview
Class Central Tips
By the end, you will be able to build a convolutional neural network, including recent variations such as residual networks; apply convolutional networks to visual detection and recognition tasks; and use neural style transfer to generate art and apply these algorithms to a variety of image, video, and other 2D or 3D data.
The Deep Learning Specialization is our 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. It provides a pathway for you to gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take the definitive step in the world of AI.
Syllabus
- Foundations of Convolutional Neural Networks
- Learn to implement the foundational layers of CNNs (pooling, convolutions) and to stack them properly in a deep network to solve multi-class image classification problems.
- Deep convolutional models: case studies
- Learn about the practical tricks and methods used in deep CNNs straight from the research papers.
- Object detection
- Learn how to apply your knowledge of CNNs to one of the toughest but hottest field of computer vision: Object detection.
- Special applications: Face recognition & Neural style transfer
- Discover how CNNs can be applied to multiple fields, including art generation and face recognition. Implement your own algorithm to generate art and recognize faces!
Taught by
Andrew Ng
Charts
- #2 in Subjects / Computer Science / Deep Learning
- #2 in Subjects / Deep Learning / Neural Networks
Related Courses
-
Neural Networks and Deep Learning
deeplearning.ai, Stanford University
4.8 -
Deep Learning in Computer Vision
Higher School of Economics
2.3 -
Deep Neural Networks with PyTorch
IBM
-
Introduction to Deep Learning & Neural Networks with Keras
IBM
-
Deep Learning - IITKGP
Indian Institute of Technology, Kharagpur, NPTEL
-
Convolutional Neural Networks in TensorFlow
deeplearning.ai
5.0
Reviews
4.9 rating, based on 8 reviews
-
Ronny De Winter completed this course, spending 5 hours a week on it and found the course difficulty to be medium.
Yet another world-class course from Andrew Ng, the godfather of machine learning education.
He makes recent research accessible with very well structured explanations, from the core concepts towards complete solutions, including tensorflow/keras exercises to demonstrate how everything is put into practice. -
Rates
Rates completed this course, spending 3 hours a week on it and found the course difficulty to be medium.
Andrew Ng is an excellent instructor, all of these deeplearning.ai courses are well worth your time.
My only critique is some times the pedagogy is a little backward for my taste, i.e he will often teach the detail first and the intuition and the "why you should care" last - I would have preferred that to be reversed, but the content is all there none the less.
Also, all of these courses are theory based, so you should be doing your own simple projects along side these courses to make your learning more "concrete" as they say in machine learning. -
Rafael Espericueta
Rafael Espericueta completed this course.
This course was one of the best courses I've ever taken - but one can say the same for any of Andrew Ng's courses! You're not just learning about cutting edge computer vision techniques, carefully and thoroughly explained, you're gleaning the distilled wisdom of a true master of deep learning. Even one of these wisdom gems he dispenses so freely throughout his courses could have saved some DL team months of wasted work. I really can't recommend this course highly enough (and the same goes for the entire Deep Learning Specialization). -
Sergei Zaitseff
Sergei Zaitseff completed this course, spending 7 hours a week on it and found the course difficulty to be medium.
The course is based on recent research papers in the field of CNN. Lectures of prof. Andrew Ng cover even complex topics from those research papers so it its easy to understand for the student. However, the programming assignments are a bit of joke. The student is allowed to add only a couple of lines (often unimportant) to a prepared code. I understand that the topics are rather complex, but there could be ways to make it more challenging and fun not only for TAs. Still rate it 5 star for a high quality of production and excellent lectures as a good introductory course to CNNs and their recent applications. -
Anonymous
Anonymous completed this course.
Prof. Andrew Ng covers the topics in quite enough detail and explains the concepts very properly. I was really blown away by his lectures on YOLO and inception net. This course is highly recommended for anyone who has some understanding of fully connected neural nets and wants to learn about CNNs. The only issue I think about this course is that the programming assignments do a lot of babysitting, making them very easy which is good for beginners but not for the intermediate students. -
Raivis Joksts
Raivis Joksts completed this course, spending 6 hours a week on it and found the course difficulty to be easy.
Keeping in the same quality as the previous courses in this specialisation, this is a good introduction to CNNs. Once again there is quite a bit of math, but this should not be a deterrent, as the main idea is still presented well. Practical tasks focus a lot on implementing the "under the hood" mechanics of certain deep learning steps, which I personally did not enjoy as modern frameworks do that for you. -
Y. Nicodeme completed this course, spending 5 hours a week on it and found the course difficulty to be medium.
A nice course on convolutional neural networks, face recognition and neural style transfer. it contains tensorflow and keras hands-on examples -
Anonymous
Anonymous completed this course.
Explained really good, programming assignments are plentiful and there are a lot of links and papers which are given for those who want.
Never Stop Learning!
