Programming A Neural Network: Regression in Keras

Author(s): Adam Ross Nelson

Originally published on Towards AI.

A detailed tutorial and walk through classic of the house price prediction task

This member-only story is on us. Upgrade to access all of Medium.

As you move through your data science learning journey it is important to balance the time you spend on learning theory against the time you spend on learning to code, apply, or implement. I am a strong proponent of not racing to the .predict() method.

Image credit: Author’s illustration created in Canva. Futuristic houses. In this tutorial you will use Keras to predict housing prices.

Previously I have warned that many data science bootcamps (and by implication also tutorials) operate or feel like a race to the .predict() method. If you are following along with this tutorial series we saved the .predict() method for this, third, installment. In the previous two installments we:

Looked at the math underlying neural networks and also surveyed important points in the historical development of artificial neural networks. Programming a Neural Network Tutorial: Vintage Style.We also looked at backward propagation. Importantly the second installment on backward propagation also provided a detailed look at key terms and phrases in the science of artificial neural networks. Programming a Neural Network Tutorial: Backward Propagation.

If you have found this installment of the tutorial please consider reviewing the previous two installments before… 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