Want to see what the fuss is all about? Looking to master the technical content to advance your career or start your own company? I explored the open source project Class Central and found 31 online courses (15 of which are completely free) that cover everything from the basics of deep learning to the most cutting-edge research today.
Before we start, you may be asking yourself: "What exactly is deep learning?" Here's a succinct description:
"Deep learning is a subfield of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural networks."
We cover the basic components of deep learning, what it means, how it works, and develop code necessary to build various algorithms such as deep convolutional networks, variational autoencoders, generative adversarial networks, and recurrent neural networks. A major focus of this course will be to not only understand how to build the necessary components of these algorithms but also how to apply them for exploring creative applications. Free and paid options are available.
Prominent review (by Christopher Kelly): "I have an undergraduate degree in computer science ... I've spent a ton of time on Khan Academy and Coursera and I'm blown away by the quality and professionalism of the content of this course. Highly recommended!"
Learn about artificial neural networks and how they're being used for machine learning, as applied to speech and object recognition, image segmentation, modeling language, and human motion, etc. We'll emphasize both the basic algorithms and the practical tricks needed to get them to work well. Free and paid options are available.
Prominent review (by Bobby Brady): "This is one of those chance in a lifetime course you have to get to learn from the greats. Geoffrey Hinton was one of the most important and influential researchers to work on artificial intelligence and neural nets back in the 80's. Currently, he is working with Google in their AI/deep learning initiatives."
This 7-week course is designed for anyone with at least a year of coding experience, and some memory of high-school math. You will start with step one - learning how to get a GPU server online suitable for deep learning - and go all the way through to creating state of the art, highly practical, models for computer vision, natural language processing, and recommendation systems. Free.
Prominent review (by Anonymous): "This is really a hidden gem in a field that rapidly growing. Jeremy Howard does an excellent job of both walking through the basics and presenting state of the art results. I was surprised time and again when not only was he presenting material developed within the last year, but even during the week the course was running ... You practice on real-life data through Kaggle competitions. I would strongly recommend this course to anyone looking to go from zero real-world experience to competing with experts in the field."
A week-long intro to deep learning methods with applications to machine translation, image recognition, game playing, image generation and more. A collaborative course incorporating labs in TensorFlow and peer brainstorming along with lectures. Free.
This class is an introduction to the practice of deep learning through the applied theme of building a self-driving car. It is open to beginners and is designed for those who are new to machine learning, but it can also benefit advanced researchers in the field looking for a practical overview of deep learning methods and their application. Free.
In this course, you'll develop a clear understanding of the motivation for deep learning, and design intelligent systems that learn from complex and/or large-scale datasets. You will learn to solve new classes of problems that were once thought prohibitively challenging and come to better appreciate the complex nature of human intelligence as you solve these same problems effortlessly using deep learning methods. Free.
This is an applied course focusing on recent advances in analyzing and generating speech and text using recurrent neural networks. The mathematical definitions of the relevant machine learning models are introduced and their associated optimization algorithms are derived.
The course, which is free, is lead by Phil Blunsom and delivered in partnership with the DeepMind Natural Language Research Group.
The course provides a thorough introduction to cutting-edge research in deep learning applied to NLP. On the model side, we will cover word vector representations, window-based neural networks, recurrent neural networks, long-short-term-memory models, recursive neural networks, convolutional neural networks as well as some recent models involving a memory component. Through lectures (note: Winter 2017 videos now posted) and programming assignments students will learn the necessary engineering tricks for making neural networks work on practical problems. Free.
This course is a deep dive into details of the deep learning architectures with a focus on learning end-to-end models for these tasks, particularly image classification. During the 10-week course, students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. The final assignment will involve training a multi-million parameter convolutional neural network and applying it to the largest image classification dataset (ImageNet). We will focus on teaching how to set up the problem of image recognition, the learning algorithms (e.g. backpropagation), practical engineering tricks for training and fine-tuning the networks and guide the students through hands-on assignments and a final course project. Free.
This course focuses on the exciting field of deep learning. By drawing inspiration from neuroscience and statistics, it introduces the basic background of neural networks, backpropagation, Boltzmann machines, autoencoders, convolutional neural networks, and recurrent neural networks. It illustrates how deep learning is impacting our understanding of intelligence and contributing to the practical design of intelligent machines. Free.
Various organizers (including Yoshua Bengio and Yann LeCun) via Independent
Deep Learning Summer School is aimed at graduate students and industrial engineers and researchers who already have some basic knowledge of machine learning (and possibly but not necessarily of deep learning) and wish to learn more about this rapidly growing field of research.
It isn't organized like a traditional online course, but its organizers (including deep learning luminaries such as Bengio and LeCun) and the lecturers they attract make this series a gold mine for deep learning content. It is free.
The further one dives into the ocean, the more unfamiliar the territory can become. Deep learning, at the surface, might appear to share similarities. This course is designed to get you hooked on the nets and coders all while keeping the school together. Free.
The majority of data in the world is unlabeled and unstructured. Shallow neural networks cannot easily capture relevant structure in, for instance, images, sound, and textual data. Deep networks are capable of discovering hidden structures within this type of data. In this TensorFlow course, you'll use Google's library to apply deep learning to different data types in order to solve real-world problems. Free.
In this course, you'll gain hands-on, practical knowledge of how to use neural networks and deep learning with Keras 2.0, the latest version of a cutting-edge library for deep learning in Python. Partially free.
The following courses, sorted by rating, are all hosted on Udemy. Prices vary depending on Udemy discounts, which are frequent. You are often able to purchase access for as little as $10.
Please note that the offerings from Lazy Programmer Inc. come with a suggested order as per the "Useful Course Ordering" guideline in their course descriptions.
Kirill Eremenko and the SuperDataScience Team via Udemy
Learn to create deep learning algorithms in Python from two machine learning and data science experts. Templates included. This course is taught by the same instructor that teaches my top recommendation for the intro to data science courses.
A guide for writing your own neural network in Python and Numpy, and how to do it in Google's TensorFlow.
Artificial Intelligence is transforming our world in dramatic and beneficial ways, and Deep Learning is powering the progress. Together with Siraj Raval, Udacity provides a dynamic introduction to this amazing field, using weekly videos, exclusive projects, and expert feedback and review to teach you the foundations of this future-shaping technology.