chapter four

4 Dipping toes in Deep Learning

 

This chapter covers

  • Implementing popular deep learning algorithms (i.e. fully connected networks, convolution neural networks and recurrent networks) using Keras
  • Training the models defined with Keras using appropriate datasets
  • Understanding and tweaking various parameters in Keras in order to improve model performance

Deep learning is a broad term that has many different algorithms under its wings. Deep learning algorithms come in many different flavors and colors. They can be classified by many criteria; the type of data they consume (e.g. structured data, images, time-series data), depth (shallow, deep and very-deep), etc. The main types of deep networks we are going to discuss, and implement are,

  • Fully connected networks
  • Convolution neural networks
  • Recurrent neural networks

Having the knowledge to comfortably implement the above types of neural networks are a key skill to be successful in the field, whether you are a graduate student, a data scientist or a research scientist. This knowledge directly extends to becoming skillful in implementing more complex deep neural networks that deliver state-of-the-art performance in various problem domains.

4.1 Fully connected networks

4.1.1 Understanding the data

4.1.2 Autoencoder model

4.2 Convolution neural networks

4.2.1 Understanding the data

4.2.2 Implementing the network

4.3 One Step at a Time: Recurrent neural networks

4.3.1 Understanding the data

4.3.2 Implementing the model

4.3.3 Predicting future CO2 values with the trained model

4.3.4 Summary

4.4 Answers