Blog‎ > ‎

15 Deep Learning Open Courses & Tutorials

posted Jan 29, 2018, 8:17 PM by MUHAMMAD MUN`IM AHMAD ZABIDI   [ updated Jan 29, 2018, 8:30 PM ]
Credit to [https://sky2learn.com/deep-learning-reinforcement-learning-online-courses-and-tutorials-theory-and-applications.html]


Deep learning and deep reinforcement learning have recently been successfully applied in a wide range of real-world problems. Here are 15 online courses and tutorials in deep learning and deep reinforcement learning, and applications in natural language processing (NLP), computer vision, and control systems. 12 of them include video lectures. The courses cover the fundamentals of neural networks, convolutional neural networks, recurrent networks and variants, difficulties in training deep networks, unsupervised learning of representations, deep belief networks, deep Boltzmann machines, deep Q-learning, value function estimation and optimization, and Monte Carlo tree search. Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville is a great open access textbook used by many of the courses, and Daivd Silver provides a good series of 10 video lectures in reinfrocement learning. For machine learning reviews, here are 15 online courses and tutorials for machine learning.

Deep Learning Specialization

Andrew Ng. Founder of Coursera. Coursera. 2017

This is a series of five sub-courses, teaching the fundamental of deep learning as well as how to apply deep learning in various areas, for example, healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will gain hands-on experiences in using TensorFlow to solve real problems. The course has video lectures.

Deep Learning

Ruslan Salakhutdinov. Carnegie Mellon University, Director of AI Research at Apple. 2017.

This course starts with the basic topics ranging from feedforward neural nets, backpropagation, convolutional models. Then the essentials of deep learning are introduced, including directed and undirected graphical models, independent component analysis (ICA), sparse coding, autoencoders, restricted Boltzmann machine (RBMs), Monte Carlo Methods, deep belief networks, deep Boltzmann Machines, and Helmholtz Machines. Additional topics include regularization and optimization in deep net, sequence modeling, and deep reinforcement learning.

Theories of Deep Learning

David Donoho, Hatef Monajemi, and Vardan Papyan. Stanford University. 2017.

This course discusses theoretical aspects of deep learning. There are 8 invited guest lectures from the leading scholars in the deep learning, computational neuroscience, and statistics. You will have a chance to explore their diverse and interdisciplinary viewpoints for the current research trends in deep learning. The course has video lectures.

Deep Learning

Yoshua Bengio. Université de Montréal, Head of the Montreal Institute for Learning Algorithms (MILA). 2016

The course reviews the basics of neural networks, including perceptrons, backpropagation and gradient optimization. It then covers advanced subjects in neural networks, probabilistic graphical models, deep networks, and representation learning.

Deep Learning and Reinforcement Learning Summer School 2017

This summer school organized by Yoshua Bengio and his colleagues. Université de Montréal, Head of the Montreal Institute for Learning Algorithms (MILA). 2016

The summer school covers two tracks, deep learning and reinforcement learning. The invited speakers are leading scholars and researchers in these fields. They cover the fundamental knowledge of deep learning and reinforcement learning. In addition, both tracks also discuss the most recent research trends and discoveries in these areas. The summer school includes video lectures.

Deep Reinforcement Learning

Sergey Levine. University of California at Berkeley. 2017.

The course covers the basics of reinforcement learning: Q-learning and policy gradients. It also includes the advanced model learning and prediction, distillation, reward learning, as well as advanced deep RL, for example, trust region policy gradients, actor-critic methods, exploration. This course has video lectures.

Deep Learning

Vincent Vanhoucke. Principal Scientist at Google and Director of the Brain Robotics Research team, and Arpan Chakraborty. Google via Udacity. 2017.

The course covers deep learning, deep neural networks, convolutional neural networks and deep models for text and sequences. The assignments will require you to use TensorFlow for practical experiences. The course has video lectures.

Deep Learning for Natural Language Processing

Phil Blunsom at University of Oxford, Chris Dyer at Carnegie Mellon University, Edward Grefenstette at DeepMind, Karl Moritz Hermann at DeepMind, Andrew Senior, Wang Ling at DeepMind, and Jeremy Appleyard at Nvidia. University of Oxford. 2017.

The course covers the fundamentals of deep learning and how it applies in natural language processing. You will learn how to define mathematical problems in this field, as well as to get hands-on programming experience in CPU and GPU. This course includes video lectures.

Convolutional Neural Networks for Visual Recognition

Fei-Fei Li. Stanford University, Director of Stanford AI Lab and Chief Scientist AI/ML of Google Cloud. 2017.

The course will cover the basics of deep learning, and how to apply deep learning techniques in computer vision. Students will get hands-on experience in how to train and fine-tune neural networks through the assignments and the final project. Python will be mainly used in the course. This course includes video lectures.

Deep Reinforcement Learning and Control

Ruslan Salakhutdinovat Carnegie Mellon University, Director of AI Research at Apple and Katerina Fragkiadaki at Carnegie Mellon University. Carnegie Mellon University. 2017.

This course topics cover the fundamentals of deep learning, reinforcement learning, Markov decision process (MDPs), Partially observable Markov decision process (POMDPs), Temporal difference learning, Q learning, deep learning, deep Q learning. Advanced topics include optimal control, trajectory optimization, Hierarchical RL and Transfer Learning.

Tutorial: Deep Reinforcement Learning, RLDM 2015

David Silver at Google DeepMind. 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM), Edmonton 2015.

In this 1.5-hour video tutorial, you will understand the fundamentals of deep learning, reinforcement learning, and how to combine DL and RL with various approaches: i.e., deep value functions, deep policies, and deep models. Besides, you will also learn from the leading expert that how to handle the divergence issues in these methods.

Tutorial: Deep Learning, Simons Institution, 2017

Ruslan Salakhutdinov. Carnegie Mellon University, Director of AI Research at Apple. 2017.

This tutorial consists of four 1-hour-long video lectures, giving students a quick and in-depth introduction to deep learning. It covers from supervised learning to unsupervised learning, as well as model evaluation and open research questions in deep learning.

Tutorial: Deep Reinforcement Learning, Simons Institution 2017

Pieter Abbeel. University of California at Berkeley. 2017.

This one-hour long tutorial on deep reinforcement learning, with a video lecture. You will have a glance of how deep reinforcement learning works.

Youtube: Deep Reinforcement Learning, MLSS 2016

John Schulman, Research scientist at OpenAI. Machine Learning Summer Schools - MLSS. 2016.

This tutorial includes four one-hour long video lectures with the practice in a lab problem.

Youtube Lecture Collection | Natural Language Processing with Deep Learning (Winter 2017)

Christopher Manning at Stanford University and Richard Socher,Chief scientist at Salesforce. Stanford University. 2017.

This is the archived version of "CS224n: Natural Language Processing with Deep Learning", taught in Winter 2017 at Stanford, with eighteen video lectures. There is also an ongoing version of the course, starting in 2018. It discusses how to apply deep learning in natural language processing, as well as issues in NLP and limits of deep learning for NLP.

Comments