Summary

In this chapter, we introduced the autoencoder, an effective dimensionality reduction technique with some unique applications. We focused on the theory behind the stacked denoised autoencoder, an extension of autoencoders whereby any number of autoencoders are stacked in a deep architecture. We were able to apply the stacked denoised autoencoder to a challenging natural language processing problem and met with great success, delivering highly accurate sentiment analysis of hotel reviews.

In the next chapter, we will discuss supervised deep learning methods, including Convolutional Neural Networks (CNN).