Andrew Ng: deep learning special
This series focuses on basic courses to explain the depth of learning and applying ways in different areas, such as health care, autopilot, sign language, reading, music generation, and natural language processing. Curriculum contains five sub-courses, video lectures. At the same time, users will get to use TensorFlow course to solve practical problems of practical experience.
Links: https://www.coursera.org/specializations/deep-learning
CMU: deep learning
The course is led by Ruslan Salakhutdinov Apple, director of the Institute of Artificial Intelligence. Course begins to explain some of the basics such as feed-forward neural networks, back-propagation, such as convolution model. Then introduce the depth points in the study, including the model of FIG, independent component analysis (the ICA), sparse coding, automatic and non encoder to FIGS restricted Boltzmann machine (the RBM), Monte Carlo method, the depth of belief networks , Boltzmann machine and the depth of the Helmholtz machine. Other networks include the depth of regularization and optimization, modeling sequence and depth of reinforcement learning.
Links: http://www.cs.cmu.edu/~rsalakhu/10707/
Stanford University: deep learning theory (Stat385)
This course discusses the theoretical aspects of knowledge of deep learning. There are eight special guest lectures, these guests are deep learning, scientific computing and statistical leaders in terms of nerves. You will have the opportunity to study in depth in view of the current research trends, discover the diversity of their perspectives and interdisciplinary. This course has video lectures.
Links: https://stats385.github.io/
Yoshua Bengio: deep learning
The course is led by the University of Montreal. First course reviews the basics of neural networks, including perceptron, back-propagation algorithm and gradient optimization. Then introduces the neural network, the frontiers of knowledge probabilistic graphical models, such as the depth of the network and learns.
Links: https://ift6266h16.wordpress.com/
UC Berkeley: the depth of reinforcement learning
The course includes strengthening the basics of learning: Q- learning strategies and gradient, and also includes advanced learning and prediction model, extraction, reward learning, and advanced depth of reinforcement learning, such as trust domain policy gradient method, actor-critic method, explore ways . This course has video lectures.
Links: http://rll.berkeley.edu/deeprlcourse/
Google & Udacity: deep learning
The course Vincent Vanhoucke by the Google chief scientist and co-founder of Udacity of Arpan Chakraborty. The course includes deep learning, deep neural networks, neural networks and deep convolution model for text and sequences. Course work required tensorflow. This course has video lectures.
Links: https://cn.udacity.com/course/deep-learning--ud730
Stanford University: Based on natural language processing depth learning (CS224n)
The course is 2017 Winter Stanford University: Course "cs224n depth study of natural language processing" compressed version, but also a continuation of the course of 2018 edition of Stanford University. In the course discusses how natural language processing, natural language processing and limit the use of deep learning in natural language processing depth learning applications. Lecturer Christopher Manning and Richard Socher.
Links: https://www.youtube.com/playlistlist=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6
Oxford University: natural language processing depth study
This course covers the basic principles of the depth of learning and how to apply it in natural language processing. Users will learn how to define mathematical problems in this field, as well as gain experience using the CPU and GPU of the actual programming. Lecturers were from Oxford University, CMU, DeepMind and NVIDIA. This course includes a video lecture.
Links: https://github.com/oxford-cs-deepnlp-2017/lectures
Li Feifei: visual recognition of convolutional neural network (cs231n)
This course will cover the basics of deep learning, and how deep learning technology used in computer vision. Students will gain practical experience and training on how to fine-tune the neural network through assignments and final project. The course is mainly used Python language. The course includes a video lecture.
Links: http://cs231n.stanford.edu/
CMU: Getting deep learning
This course is led by Ruslan Salakhutdinov Apple's director of Institute of Artificial Intelligence, the depth of learning to do a quick and thorough introduction. When the curriculum is divided into four one hour long video lectures, covering supervised learning, unsupervised learning content, as well as assessment model and open research issues such as the depth of learning.
Links: https://simons.berkeley.edu/talks/tutorial-deep-learning
RLDM: to strengthen the depth learning portal
Course led by DeepMind of David Silver, published in the second reinforcement learning and decision making multidisciplinary conference (RLDM) on. In this half-hour video tutorial, users will learn the depth of learning, and strengthen the basic principles of learning, and how deep learning and reinforcement learning combined in various ways: that is a function of the depth value, depth, strategy, and depth model. In addition, users can also learn from top experts in how to deal with the problem of divergence of these methods.
Links: http://videolectures.net/rldm2015_silver_reinforcement_learning/
UC Berkeley: to strengthen the depth learning portal
This is a tutorial to learn about strengthening the hour-long, equipped with video lectures. Users will be able to see how much reinforcement learning.
Links: https://simons.berkeley.edu/talks/pieter-abbeel-2017-3-28
MLSS: to strengthen the depth learning portal
Course led by OpenAI our research scientists, John Schulman, including four one-hour long video lectures and practice for the laboratory with the problem.
Links: https://www.youtube.com/playlistlist=PLjKEIQlKCTZYN3CYBlj8r58SbNorobqcp