PrincetonPy: Introduction to Tensorflow, 3/1/17
The next PrincetonPy session will be devoted to the TensorFlow library.
TensorFlow is a Python Library open sourced by Google that allows researchers to express arbitrary computation as a graph of data flows. Nodes in this graph represent mathematical operations, while edges represent data that is communicated from one node to another.
After a brief introduction to the TensorFlow architecture and the primitives used in the library we will work through the linear regression and CNN examples, discuss alternative APIs (Keras), and ways to train distributed models on a cluster.
Alexey Svyatkovskiy is a Big Data, Software and Programming Analyst with the Princeton Institute for Computational Science & Engineering (PICSciE). He holds a PhD in particle physics and has over 5 years of experience in large scale data analysis and machine learning. His work has been presented at IEEE Big Data conference and Spark Summit.
Location: Room 347, Visualization Lab
Date/Time: 03/01/17 at 4:00 pm - 03/01/17 at 5:00 pm
Category: PrincetonPy Group Talks