Author(s): Günter Röhrich

Originally published on Towards AI.

Stepping through theory, background, and code examples

Neural networks have gained incredible attention over the last decade (despite being around for much longer), and seem to have made incredible progress in the eyes of the public. This is especially true for the huge language models that seem to have gained all the media’s attention.

While discussion about deep learning seems to be everywhere now, I also have the strong impression that this whole field of artificial intelligence appears to be a huge black-box topic.

Deep learning is impressive but no magic. In this post, I will go over a few theoretical aspects of what a neural network is and how it can be used to achieve great things, such as predicting values and sequences (e.g., like a language model) or classifying images with just a few lines of code.

Coffee-Wave by Dall-E, prompt by author

What will we be looking at:

Theory of Neural NetworksHow does a neural network work?What are types of neural networks?What are applications of neural networks?Activation functionsImplementations in PyTorch and TensorFlowWhere is Deep Learning goingConclusion

To start with the theory, a neural network is a computational model that is inspired by the structure and function of biological neurons — this may sound incredibly theoretical, but the only purpose of… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI