Six Types of Neural Networks that you must know about
Ranging from CNN, RNN, Transformer to GANs
Neural Nets have become pretty popular today. Yet still, I see that there is a dearth of understanding about them. For one, I have seen a lot of people not being able to recognize the various types of Neural Networks and the problems they solve, let alone distinguish between them. And second, which is somehow even worse, is when People just toss the words “Deep Learning” to specify all of these without really understanding what they really entail.
In this post, I will talk about the most famous neural network architectures that I believe product owners, as well as practitioners, should be familiar with to make everyone’s life a little bit easier.
1. Feed-Forward Neural Network
This is the most basic type of Neural network that was made popular by the current technological advancements which allowed us to add many more hidden layers without worrying too much about computational time and also by the discovery of the Backpropagation algorithm by Geoff Hinton in 1990.
They essentially consist of an input layer, multiple hidden layers and an output layer. In this type of Neural networks, there is no loop and information only flows forward. This type of neural network…
