Unsupervised Representation Learning

In this chapter, we will cover the following recipes:

• Using denoising autoencoders to detect fraudulent transactions
• Generating word embeddings using CBOW or skipgram representations
• Visualizing the MNIST dataset using PCA and t-SNE
• Using word vectors for Twitter sentiment analysis
• Implementing LDA with scikit-learn
• Using LDA to classify text documents
• Preparing data for LDA