Feature Learning with Matrix Factorization and Neural Networks

Our speaker Aaron Richter began as a programmer before moving into data pipelining and analytics where he found a love for data science. He is currently working on a Computer Science PhD focusing on Data Mining & Machine Learning as well as being a practicing data scientist for Modernizing Medicine (http://modmed.com (http://modmed.com/)), an innovative EHR system for several surgical specialties.

In this meetup we will discuss feature learning. 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 are 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