I found a great YouTube playlist of videos on deep learning. You can go at your own pace as all videos are under 10 minutes long.
You will be introduced to deep learning without all the super-complicated maths and fairly quickly get to a point where everything starts to “click”.
They also have a Facebook page you should definitely like and follow at https://www.facebook.com/DeepLearningTV
Video 1/30 – Introduction
Are you overwhelmed by overly-technical explanations of Deep Learning? If so, this series will bring you up to speed on this fast-growing field – without any of the math or code. Deep Learning is an important subfield of Artificial Intelligence (AI) that connects various topics like Machine Learning, Neural Networks, and Classification.
2/30 What is a Neural Network?
With plenty of machine learning tools currently available, why would you ever choose an artificial neural network over all the rest? This clip and the next could open your eyes to their awesome capabilities! You’ll get a closer look at neural nets without any of the math or code – just what they are and how they work.
3/30 Three Reasons to go Deep
With so many alternatives available, why are neural nets used for Deep Learning? Neural nets excel at complex pattern recognition and they can be trained quickly with GPUs. Historically, computers have only been useful for tasks that we can explain with a detailed list of instructions.
4/30 Your Choice of Deep Net
Deep Nets come in a large variety of structures and sizes, so how do you decide which kind to use? The answer depends on whether you are classifying objects or extracting features. Let’s take a look at your choices.
5/30 An Old Problem
If deep neural networks are so powerful, why aren’t they used more often? The reason is that they are very difficult to train due to an issue known as the vanishing gradient. To train a neural network over a large set of labelled data, you must continuously compute the difference between the network’s predicted output and the actual output.
6/30 Restricted Boltzmann Machines
So what was the breakthrough that allowed deep nets to combat the vanishing gradient problem? The answer has two parts, the first of which involves the RBM, an algorithm that can automatically detect the inherent patterns in data by reconstructing the input.
7/30 Deep Belief Nets
An RBM can extract features and reconstruct input data, but it still lacks the ability to combat the vanishing gradient. However, through a clever combination of several stacked RBMs and a classifier, you can form a neural net that can solve the problem. This net is known as a Deep Belief Network.
I hope you love this series as much as I do. If you want to see the remaining 23 videos, please click the button below:
Books on Deep Learning
Here are some book suggestions, in case you want to dive deeper into deep learning (pun intended).