Neural network tutorial - [Part 3] - Beyond the basics using Keras
Sure the basic building blocks are nice but how to do I build those fancy deep learning models?
In this video we take the basic linear model we developed in the last few videos and, using keras, make it non-linear. I also go over how to stack layers and add additional nodes to your model so you can begin to represent more interesting non-linear relationships within your dataset. Definitely checkout the keras website (https://keras.io/) for more details and stay tuned for other videos using keras in the future!
In this video I show the practical implications of scaling your input and output data and how that affects fitting.
Things shown:
1) how to take the basic numpy model and convert it to keras code
2) how to go from linear to non-linear activation functions
3) how to stack layer more layer and add more nodes
If you want to see a more particular non-linear example using Keras or have questions about other models/frameworks leave them in the comments.
Also check out some other helpful channels and videos on the broader topics of machine learning and cool math stuffs:
Note: Neural networks are not the best method for fitting a line there is a much more direct way for doing this which is exactly what most math libraries use. This is just to build up understand of neural networks.