21 Deep Learning Videos, Tutorials & Courses on Youtube from 2016
Until a few years back, deep learning was considered of a lesser importance as compared to machine learning. The emergence of neural networks & big-data has made various tasks possible.
Back in 2009, deep learning was only an emerging field and only a few people recognized it as fruitful area of research. But soon it gained momentum and is used today for several applications. Speech recognition, image recognition, finding patterns in a dataset, object classification in photographs, character text generation, self-driving cars and many more. Hence it is important to be familiar with deep learning and its concepts.
To make it easier for you to learn deep learning, I have curated list of youtube videos, tutorials and courses on deep learning from 2016. The list includes talks & tutorials from deep learning summer school, summits, and conference.
I hope you will find this helpful.
Who can benefit from these videos?
The videos have been shortlisted for beginners, intermediates and experts in deep learning.
The article has been divided into sections for each one of you. If you a novice or intermediate in deep learning then start with the first section. If you want to master deep learning then this article will be your best resource. First, make a schedule and start learning deep learning. I bet in few weeks you will at least be able to build your first model in deep learning.
For experts in deep learning, the advanced section contains good videos for you to enhance your knowledge. The 5 mins videos in the beginners will be a good refresher for you.
For all deep learning / data science enthusiasts you will love the applications of deep learning and examples segregated in a separate section. There are videos on Google Deepmind, learn to paint using deep learning and how deep learning is making self-driving cars a reality.
There is also a small section on reinforcement learning with one of its applications.
Table of Content
- Tutorials for Beginners on Deep Learning
- Deep Learning Simplified
- Bay Area Deep Learning School 2016 – Day 1
- Bay Area Deep Learning School 2016 – Day 2
- Tutorial Deep Learning
- Deep Learning with Neural Networks & Tensorflow Introduction
- Neural Networks for Machine Learning
- Intro to TensorFlow
- Neural Networks
- Neural Network that Changes Everything
- Wide & Deep Learning with TensorFlow – Machine Learning
- Introduction to Deep Learning
- Deep Learning Demystified
- Deep Learning Advanced
- Deep Learning Summer School, Montreal 2016
- Deep Learning Tutorial – Advanced
- Deep Learning in Practice – Speech Recognition and Beyond
- Applications of Deep Learning
- Google’s Deepmind Explained
- Self-Driving Cars and Deep Learning GPUs – NVIDIA
- 9 Cool Deep Learning Applications
- Deep Learning Program learns to Paint
- Reinforcement Learning
- Introduction to Reinforcement Learning with Function Approximation – Tutorial
- Deep Reinforcement Terrain Learning
Tutorials for Beginners on Deep Learning
If the complicated terminologies makes it difficult for you to learn deep learning, then this tutorial will prove to be a boon for you. This is a simplified tutorial on deep learning and its basic concepts. You will learn about neural networks, deep net, deep belief nets, convolutional neural networks, H2O.ai and This tutorial will give you a basic understanding about deep learning. You will also learn about different kind of models, why & when to choose each one of them. Then it will provide you hands on experience on deep learning with different use cases. You will also learn about different platforms where you can build your own deep nets and the different libraries available for deep learning. The tutorial is devoid of any mathematical calculations or coding and is best for anyone looking to get a basic idea about deep learning.
Duration: 10 hours 33 mins
As Andrew Ng correctly puts it, Deep Learning is changing the industry landscape and there is a lot of interesting deep learning applications. This video showcases Day 1 of Bay Area Deep Learning School 2016. It covers talks on Introduction on Feedforward Neutral Network by Hugo Larochelle, Deep Learning for Computer Vision by Andrej Karpathy, Deep Learning for NLP by Richard Socher, Tensorflow Tutorial by Sherry Moore, Foundations of Deep Unsupervised Learning by Ruslan Salakhutdinov and Nuts and Bolts of Applying Deep Learning by Andrew Ng. All the deep learning experts have explained the underlying concepts of deep learning in a simplified manner to give you a basic understanding of deep learning. They share use case problems to explain the real-life application of deep learning for each topic.
Duration: 10 hours 33 mins
This is the Day 2 video of Bay Area Deep Learning school. It showcases talks on Foundation of Deep Reinforcement Learning by John Schulman, Introduction to Theano: A Fast Python library for Modelling & Training by Pascal Lamblin, Speech Recognition and Deep Learning by Adam Coates & Vinay Rao, Machine Learning with Torch & Autograd by Alex Wiltschko, Sequence to Sequence by Deep Learning by Quoc Le, Foundation and Challenges of Deep Learning by Yoshua Bengio. These deep learning practitioners are most searched deep learning practitioners and serve with companies like Google Brain, Twitter to name a few.
Duration: 2 hours 29 mins
In this tutorial on Deep Learning Yoshua Bengio and Yann Lecun explains the breakthroughs brought by deep learning in the recent years. After their in-depth research of 30 years, Yoshua & Yann share the insights on how deep learning has transformed machine learning & AI. In this tutorial, you will learn how deep learning allows computational models composed of multiple processing layers to learn representation of data. These methods have improved speech recognition, visual object recognition, object detection and domains like genomics. This tutorial will take you through the basics of deep learning, discuss its various applications and what challenges it poses in front of us.
If you have been wondering how neural network works and why recently there is so much of uproar created by them. In this tutorial on introduction to neural networks, you will learn how neural network are able to create powerful models with huge datasets. Understand the structure of neural networks and how each input layer combines together to generate an output. This is the only first video of the complete tutorial, for TensorFlow Basics watch part 2 of the tutorial. To know how to build a neural network model, continue watching part 3 and so on.
The main idea behind studying artificial neural networks is to understand the style of parallel computation of neurons and their adaptive connections. In this course by Prof. Geoffrey Hinton taught at University of Toronto you will learn how neural networks and machine learning can bring a revolution in technology. It includes topics such as perceptrons, back propagation, CNN, RNN, gradient descent, bayesian optimization of hyperparameters and many more topics. This is one of the best courses available out there on deep learning. If you are a deep learning enthusiast, you can’t just afford to miss it.
One of the most popular machine learning library right now is TensorFlow. Though it was built for conducting machine learning and deep neural network research primarily. But because of its versatility, Tensorflow can be used in variety of applications. Here in this interesting tutorial on TensorFlow you will learn to build a handwritten digit image classifier in Python in under 40 lines of code. You will also learn how to generate music in TensorFlow, what is Tensorboard, build a neural network and pros & cons of using TensorFlow over other deep learning libraries. This brief tutorial on TensorFlow is a must watch for any novice in deep learning.
Artificial neural network are capable of learning and they need to be trained. There are basically 3 steps for building a machine learning model – build it, train it and test it. Once the model is built it can be trained to become better & better at pattern recognition. In these quick 5 min videos, you will learn to build neural network, build autoencoders and build a recurrent neural network. The codes for each video is also available in the description on youtube.
Duration: 14:16 mins
Convolutional neural networks is a combination of deep neural networks and kernel convolutions. In this video, it is explained how convolutional neural networks is a step change in image classification accuracy. If you are a deep learning enthusiast with very little knowledge of neural networks, watch this video. It will explain how deep learning is used to estimate the price of a house.
Duration: 3:24 mins
Wide and deep learning combines the power of memorization and generalization used for training wide linear models and deep neural networks. In this video, learn about the implementation of this in easy to use API in TensorFlow. They are useful for large scale regression and classification problems with sparse inputs like recommendation system, search and ranking problems. Explore the possibilities of wide and deep learning with this video.
Duration: 11 mins
This video will provide you a mathematical explanation to deep learning. It will take you through a basic introduction on how machines find the grouping of different variables and take decisions. If you are a mathematics person then this will be an apt explanation for you to parameters of model building. It very easily explains neural networks and how the varied input variables affect an output.
Duration: 22:18 mins
This tutorial on deep learning is a beginners guide to getting started with deep learning. In this tutorial, you will learn how deep learning is beneficial for finding patterns. Learn about neural networks with a simplified explanation in simple english. It will first introduce you to the structure of neuron and how they work. Then it proceeds further to explain how all neurons form a pattern within each other. Then learn about the various applications of deep learning in real life.
Deep Learning – Advanced
The Deep Learning summer school of Montreal saw experts and practitioners of deep learning from all ages group. This tutorial is aimed at individuals having basic understanding of deep learning and neural networks. Here it showcases talks on Recurrent Neural Networks by Yoshua Bengio, Theoretical neuroscience & deep learning theory by Surya Ganguli, Reasoning summit and attention by Sumit Chopra, Large Scale Deep Learning with Tensorflow by Jeff Dean, Learning Deep Generative Models by Ruslan Salakhutdinov, GPU programming for Deep Learning by Ryan Olson and many more informative talks. If you missed out on the summer school and all the informative content that was shared, here is the list of all the talk.
Duration: 1 hour 36 mins
In past few years, the techniques of image classification, segmentation, and object detection have evolved tremendously with Deep Learning. This tutorial will take you through the advance concepts of Deep Learning focusing mainly on computer vision and image processing using Theano & Lasagne. Alongside, the speaker also discusses important tips & tricks such as dealing with less training data etc. To understand concepts, prior knowledge of algebra, calculus and machine learning is required.
Duration: 34:46 mins
Andrew Ng needs no introduction, his contributions to deep learning are recognized well. He was one of the first ones to recognize the potential deep learning beholds for the world. In this one-on-one conversation with Andrew Ng, he shares his experience of working with deep learning and the technology advancements which has been brought by deep learning. He talks about how the emergence of big-data is disrupting all the industries today. Watch this complete video to know more about the future of deep learning and data science.
Application of Deep Learning
Duration: 13:44 mins
It was a historic moment when Google’s AlphaGo beat the world champion Lee Sedol in the ancient boardgame GO. It triggered a new wave of technology advancement when a machine succeeded over a human. Google Deepmind claimed to bring the next generation of AI and aims to develop programs which will be smart enough to take actions on their own. This video explains when and why Deepmind was founded. And what revolution it can bring in AI.
Duration: 1 hour 7 mins
The CEO of NVIDIA Jen-Hsun Huang shares how the deep learning and research has changed the face of self-driving cars making it a reality. He opens the talk by introducing the world’s first AI supercomputer for self-driving cars designed by NVIDIA. He explains how deep neural networks & big data has been used to solve the problem of GPUs. This video will blow your mind that how deep learning and AI is making the impossible become a reality.
Duration: 4:43 mins
Wondering what are some of the interesting the real-life applications of Deep learning and machine learning? This video showcases the real-life applications of deep learning. You will come across some intriguing applications like toxicity detection for different chemical structure, mitosis detection for large images, sequence generation, how a computer program itself plays pong and many more interesting applications.
Duration: 4:43 mins
Artificial neural networks are inspired by the human brain and the aims to study the connection between the neurons. In the above videos, we have seen several applications of deep learning. But Neural art happens to be the most amazing and surprising application of deep learning. In this video, you will learn to how to paint using deep learning or re-create famous painting using artificial neural networks. All the user needs to do is provide an input photograph and a target image from which the artistic style will be learned.
Duration: 2 hours 18 mins
Reinforcement learning is a technique developed by machine learning and research communities for making optimal sequential decision making. This tutorial will provide you a thorough understanding of the underlying formal problem (Markov decision processes) and its core solution methods, including dynamic programming, Monte Carlo methods, and temporal-difference learning. It is focussed on how these methods are combined with parametric approximation to find good approximate solutions to problems that are otherwise too large to be addressed at all. The speaker will also take you through the recent developments in function approximation, eligibility traces, and off-policy learning.
Duration: 3 mins
In this video, a combination of deep learning and reinforcement learning is depicted which is thought to be useful in solving many extremely difficult tasks. Google DeepMind built a system that can play Atari games at a superhuman level using deep reinforcement learning. This video shows an interesting use of deep reinforcement learning to teach terrain animals map their movements and avoid obstacles in the way.
This article contains a curated list of videos on deep learning and reinforcement learning. The videos have been shortlisted on the basis of the year, view count and relevance. There is ample of content on the web and we aimed to provide the most relevant videos.
Go through the list and shortlist the videos which you find suitable for you. I have tried to add all the relevant videos from 2016. But if I have missed out on any video which you think deserves a mention in the list, feel free to add them below in the comments sections. If you are a visual learner, let me know what are your thoughts on the article.
My aim is to help a larger audience to learn deep learning. Looking forward to your suggestions.