12-13, 10:30–11:00 (Asia/Jerusalem), Track 2
Generative Adversarial Networks (GANs) are a type of unsupervised learning that are well known for their ability to generate new images, videos or text, but they can also be used for a wider range of use-cases.
In this talk I will present how we used GANs at Dell for predicting the user's next activities on Dell’s website, and also cover the fundamentals of GANs, for those less familiar with it and its various applications.You should join this talk if you want to learn the basics of GANs and a less conventional way to use it for a business use-case.
The talk will start with an overview of well-known applications of GANs. I will explain the main idea of GANs: training 2 models, a Generator and Discriminator that compete against each other via a Min-Max Game formalism. We'll learn how the models train, what is a BCE loss and what are the methods for evaluation of GANs.
Lastly, I will share a use-case for GANs from my work at Dell: predicting the user’s next action on the Dell Enterprise website by using LSTM GANs.
I am a Senior Data scientist at Dell and holds a B.Sc. in Mathematics and an MBA.
In the past 3 yearsI worked with time series data like sensors coming from smartwatches and smart-phones to provide continuous health monitoring for the sick and elderly. At Dell I am working on different projects including predicting anomalies on servers, optimizing user behaviors on Dell’s website and work with hospitals (mainly radiologists) on xray anomalies classification.
My main hobbies are coffee, sport and traveling around the world!