Deep learning has become one of the hottest topics in computing in the past few years. Neural networks are not a new topic, but with the recent advances in computation capacity provided by hardware accelerators, in particular GPUs, they have gained new popularity. In this talk we present some of the concepts behind neural networks and deep learning, and then shift to the performance aspects of available solutions. We will finally focus on Tensorflow, an open source deep learning package, and provide a hands-on demo using it.
Bio- Reza Farivar is a manager at the Data Intelligence team in Capital One. He received his Ph.D. in Electrical and Computer Engineering from the University of Illinois at Urbana Champaign, working on Big Data, Clouds and Machine Learning pipeline engineering. His Postdoctoral work was on development of GPU-based learning algorithms for bioinformatics. His current work focuses on fast data streaming systems and distributed algorithms for Big Data learning and Cloud systems. He is also an adjunct assistant professor at the computer science department at the University of Illinois at Urbana-Champaign, where he teaches topics related to cloud computing and big data applications, spanning from batch and real-time processing to deep-learning and graph-based systems.
Join us tomorrow, Thursday February 23rd at 19:00 to learn about machine learning from Reza Farivar of Capital One and some of his team. As always laptops are encouraged, and there will be pizza which is provided by Capital One this week.