Garrett Hoffman, StockTwits
Garrett Hoffman is a Senior Data Scientist at StockTwits, the world’s largest social network for traders and investors, where he leads efforts to use Data and Machine Learning to understand social dynamics and provide tools for research and discovery used by a network of over one million investors. Garrett has a technical background in Math and Computer Science but believes that Data Science is really about people, using what we know or can learning about complex systems to drive optimal decisions, experiences and outcome.
Deep Learning Methods for Text Classification
This workshop will review deep learning methodologies used for text classification while working through a live example using python and TensorFlow. We will start with Representation Learning for text by exploring word2vec word embedding. We will go over the CBOW And Skip-Gram models, demonstrating how to train custom word embeddings or use pre-trained word embeddings trained on google news articles. Next, we will go over traditional Recurrent Neural Networks (RNN) and introduce improvements to the methods using Long Short-Term Memory (LSTM) cells and Gated Recurrent Units (GRUs) and explain the intuition behind why these models provide improvements in accuracy. Next discuss how Convolutional Neural Networks (CNNs) traditionally applied to Computer Vision are now being applied to Language Models. We will close out the session with some practical considerations for applying these methods to different business problems.