Meet Deci at NVIDIA GTC 2022 and Win Exclusive Prizes
March 21-24, 2022
Deci will be at NVIDIA GTC, taking place virtually on March 21-24, 2022. Our on-demand sessions will feature some of the industry's top experts, sharing their knowledge and expertise.
🎁 To celebrate this event, we invite you to enter our raffle! 🎁
3 steps for becoming eligible to win our exclusive raffle:
- Register on this page.
- Attend our sessions at GTC.
- Share a screenshot with the hashtag #DECIATGTC during the event to be eligible to win* one of six $50 Amazon gift cards or an exclusive SuperGradients model training swag kit.
*winners will be randomly selected
By submitting this form you accept the terms and conditions of the raffle.
Deci is Trusted by
Don't Miss Our Sessions at the Event
Session 1
How to Improve Model Efficiency with Hardware Aware Neural Architecture Search
Running successful and efficient inference at scale requires meeting various performance criteria such as accuracy, latency, throughput, and model size, among others.
Neural Architecture Search (NAS) holds the power to automate the cumbersome deep learning model development process, as well as quickly and efficiently generate deep neural networks that are designed to meet specific production constraints. Deci’s AutoNAC (Automated Neural Architecture Construction) technology does this by finding the best algorithm that takes into account all of the many parameters that are required to create powerful and efficient deep learning models. In this talk, we’ll cover the evolution of NAS technology and recent advances that are making NAS viable for industry applications and commercial usage. We'll outline the algorithmic optimization process with case studies and best practices for achieving best-in-class accuracy and latency results on Nvidia T4 GPU, Jetson Nano, and Xavier NX devices.
Yonatan Geifman
CEO & Co-Founder, Deci
Yonatan Geifman is the CEO and Co-Founder of Deci. Before co-founding Deci, Yonatan was a member of Google AI’s MorphNet team. He holds a PhD in Computer Science from the Technion-Israel Institute of Technology and a B.Sc. and M.Sc. in Mathematics and Computer Science from Ben-Gurion University in Israel.
His research focused on making Deep Neural Networks (DNNs) more applicable for mission-critical tasks. It has been published and presented at leading global conferences including the Conference on Neural Information Processing Systems (NeurIPS) and International Conference on Machine Learning (ICML).
Session 2
An End-to-End Walkthrough for Deploying Deep Learning Models on Jetson
Join us for a technical session packed with practical tips and tricks from model selection & training tools to running successful inference at the edge.
We will demonstrate how to benchmark different models, leverage training best practices, easily implement TensorRT based compilation and quantization all while using the latest open source libraries and other free community tools.
You will leave this talk with practical knowledge on how to cut the guesswork, quickly gain SOTA performance, maximize your Jetson devices’ compute power, and boost runtime for any AI-based application.
Nadav Cohen
VP Product, Deci
Nadav Cohen is the VP Product at Deci. Prior to Deci, Nadav worked as PM of Google’s language vertical (Dictionary & Translate) on search and assistant. He also built and managed product teams in hyper-growth startups including SparkBeyond and Tapingo. Nadav holds a MSc in Computer Science from Weizmann Institute of Science.
Ofer Baratz
DL Product Manager, Deci
Ofer Baratz is the Deep Learning Product Manager at Deci. Before Deci, Ofer spent close to 5 years at Intel developing ML & DL solutions and deploying them in production. Since last year, Ofer has been in charge of the DL engineering products at Deci focusing on the domains of training, runtime optimization, and deployment engines.