Day 2, R2 14:10–14:40
Probabilistic programming allows us to encode domain knowledge to understand data and make predictions. TensorFlow Probability (TFP) is a Python library built on TensorFlow that makes it easy to combine probabilistic models and Deep Learning. With TensorFlow 2.0, TFP can be very easily integrated into your code with very few changes and the best part - it even works with tf.keras! This talk will teach you when, why and how to use TensorFlow probability.
Slides not uploaded by the speaker.
Speaker: Niladri Shekhar Dutt
Undergraduate Researcher working in the field of Deep Learning and its applications in the field of Computer Vision and NLP. He was a visiting student at the University of California, Berkeley for Spring 2019, where he worked at the CITRIS Lab. He has won several hackathons including San Francisco DeveloperWeek Hackathon 2019 (America’s largest challenge-driven hackathon). His current research focuses on self-driving cars and training machine learning models with limited data.