MML Event #8: Feature learning using matrix factorization and neural networks

Aaron Richter will present an introduction to feature learning using matrix factorization and neural networks.

• Details:
A major step in most predictive analytics workflows is to create features from input data that can be fed into machine learning algorithms. This is often a manual and labor-intensive effort. Feature learning (also known as representation learning) allows important features to be automatically extracted from raw input data.

• Topics that will be covered:

• Manual feature engineering vs. feature learning
• Example applications of feature learning
• Matrix factorization approaches (deep dive into PCA/SVD)
• Neural network approaches (deep dive into Autoencoders and Skip-Gram/Word2Vec)
• Code samples using scikit-learn and keras

No need to bring your laptops unless you would like to, the code will be shared after the meetup.