What we're about
Upcoming events (3)
** Registration on meetup is turned off, read the instructions below to register***. We are hosting Free half-day online workshop on autoML. You can join from anywhere. RSVP: https://learn.xnextcon.com/event/eventdetails/W20052810 In this workshop, we will cover the core concepts and techniques behind AutoML. We will dive deep into the state of the art methods applied to Neural Architecture Search and Hyper parameter Parametrization. The talk will cover the fundamentals of the methods and how the different methods compare to each other. We will then spend an hour on a hand-on workshop on how to apply AutoML to real-world problems. Specifically we will walk through how to cast a problem into a classification or regression problem and then use AutoML to solve it. We will finally showcase how the AutoML solution performs as well as a hand-tuned solution. The interactive workshop offer both theoretical and practical modules. By participating in the workshop you would be able to: * Learn the core concepts behind autoML * Building deep learning models using autoML with hands-on exercise * Build a system with AutoML and deploy to production Agenda (US pacific time UTC-7): [10:00 - 10:10am] Welcome and workshop overview [10:10 - 10:45am] Core concepts behind AutoML - Neural Architecture Search and Hyperparameter Optimization [10:45 - 11:45am] Hands on AutoML workshop [11:45 - 12:00pm] Q&A and wrap up
RSVP on meetup is turned off, make sure to register here: https://learn.xnextcon.com/event/eventdetails/W20060110 Start date/time: Jun 1st, 10AM PST /1PM EST Description: "Watching paint dry is faster than training my deep learning model.” “If only I had ten more GPUs, I could train my model in time.” “I want to run my model on a cheap smartphone, but it’s probably too heavy and slow.” If this sounds like you, then you might like this talk. Exploring the landscape of training and inference, we cover a myriad of tricks that step-by-step improve the efficiency of most deep learning pipelines, reduce wasted hardware cycles, and make them cost-effective. We identify and fix inefficiencies across different parts of the pipeline, including data preparation, reading and augmentation, training, and inference. With a data-driven approach and easy-to-replicate TensorFlow examples, finely tune the knobs of your deep learning pipeline to get the best out of your hardware. And with the money you save, demand a raise! Speaker: Anirudh Koul a noted AI expert, UN/TEDx speaker, author of the Practical Deep Learning book and a former scientist at Microsoft AI & Research, where he founded Seeing AI, considered the most used technology among the blind community after the iPhone. He also serves as an ML Lead for NASA FDL and coaches a team for Roborace, the Formula One championship of autonomous driving @200mph.
** Read the instructions below to register***. We are hosting Free half-day online workshop on deep learning based for recommendation system. You can join from anywhere. RSVP: https://learn.xnextcon.com/event/eventdetails/W20052210 In this workshop, we will focus on learning how to build a real-time deep learning system. We will start with a technical talk that will dive deep into the science of recommender systems. We will cover state-of-the-art methods including deep generative recommender models. After the tech talk, we will host an interactive workshop that offers a hands-on experience. The interactive workshop offer both theoretical and practical modules. By participating in the workshop you would be able to: * Learn the core concepts behind recommender systems * Experience building deep learning models with hands-on exercise * Build a system that can actually deploy in production * Evaluate RealityEngines.AI as a solution to your AI challenges Agenda (US pacific time UTC-7): [10:00 - 10:10am] Welcome and workshop overview [10:10 - 10:45am] Core concepts behind deep-learning based recommender systems including deep generative recommender models [10:45 - 11:45am] Build all the components of the large scale real-time deep learning system [11:45 - 12:00pm] Q&A and wrap up