Introduction to deep learning: 10 free online courses recommended


Give into deep learning, in-depth learning has always been a hot topic in the audio and video industry. Here are 10 free quality online courses recommended.
We recommend you to open source project class central, which has 31 online courses (10 of which are completely free), covering from the foundation of in-depth learning to the most cutting-edge research today.

Online deep learning course
Creative Applications of Deep Learning with TensorFlow ★★★★★
This paper introduces the basic components of deep learning, its meaning, working principle, and the codes needed to develop and construct various algorithms, such as deep convolution network, variational automatic encoder, generative countermeasure network and recurrent neural network. The main focus of this course is not only to understand how to build the necessary components of these algorithms, but also to understand how to apply them to explore creative applications. Free and paid options available.
The specialty and quality of this course are very good, and it is highly recommended by many people.
Neural Networks for Machine Learning
University of Toronto
Learn about artificial neural network and how it can be used in machine learning, speech and object recognition, image segmentation, modeling language and human motion. Emphasize the basic algorithms and get the practical skills they need to work well. Free and paid options available.
What’s more powerful is the lecturer, Geoffrey Hinton, one of the most important and influential researchers who studied artificial intelligence and neural networks in the 1980s. He now works with Google on AI / deep learning projects.

It’s the grandpa who studies the godfather level in depth
Practical Deep Learning For Coders, Part 1
This 7-week course is designed for people with more than one year of programming experience. It is relatively elementary and helps you learn how to make GPU suitable for in-depth learning from 0. Free.
6.s191: introduction to deep learning
MIT (Massachusetts Institute of Technology)
The course is one week long and introduces deep learning methods, including machine translation, image recognition, games, image generation and other applications. MIT courses, free against
6.S094: deep learning of self driving cars
MIT (Massachusetts Institute of Technology)
This course introduces the practice of deep learning through the application theme of self driving cars. It is open to beginners and designed for those who are just in touch with machine learning, but senior people can also benefit from it, looking for a practical overview of deep learning methods and their applications. Free again
Deep learning of natural language processing
This course focuses on the latest development of speech and text analysis and generation using recurrent neural networks. This paper introduces the mathematical definition of related machine learning model, and deduces the related optimization algorithm.
Led by Phil blunsom and working with deepmind’s natural language research group.

Cs224n: natural language processing with deep learning Stanford University
This course comprehensively introduces the cutting-edge research of in-depth learning applied to NLP. Free Admission
CS231n: Convolutional Neural Networks for Visual Recognition
Stanford University
The course delves into the details of deep learning architecture, focusing on learning the end-to-end models of these tasks, especially image classification. During the 10 week course, students will learn how to implement, train and debug their own neural networks, and learn more about the cutting-edge research of computer vision. The final task will involve training millions of parameter convolutional neural networks and applying them to the largest image classification data set (Imagenet). This course focuses on how to set up image recognition problems, learn algorithms (such as back propagation), train and fine tune practical engineering skills of network, and guide students to complete hands-on assignments and final course projects.

Both Stanford courses are popular in the industry.
Machine Learning Nando de Freitas /University of British Columbia
The basic background of neural network, back propagation, Boltzmann machine, automatic encoder, convolutional neural network and recurrent neural network are mainly introduced. It shows how deep learning affects our understanding of intelligence and contributes to the actual design of intelligent machines.
Deep Learning Summer School 2015and2016
The audience is graduate students, engineers and researchers who already have basic knowledge of machine learning (possibly but not necessarily in-depth learning), and hope to learn more about this fast-growing research field.
It’s not organized like traditional online courses, but its organizers (including deep learning celebrities like bengio and Lecun) and the lecturers they attract make the series a gold mine for deep learning content. Free yo!

Netease Yunxin, the instant messaging and audio and video technology expert around you, understand us, please stamp Netease Yunxin’s official website
To read more industry insights and technology dry goods, please pay attention to Netease cloud blog
More exciting content, pay attention to Netease Yunxin