Demand for deep learning training is accelerating with the growing number of applications and services based on image and gesture recognition, speech recognition, natural language processing, recommendation systems, and more. The Habana® Gaudi® AI processor is designed to maximize training throughput and efficiency, while providing developers with optimized software and tools that scale to many workloads and systems.
Watch webinar recording:
In this live webinar you will learn how deep learning compute efficiencies, performance and ease of use begin at the fundamental architectural level in both hardware and software. You will be provided with specifics on how the Habana Gaudi® AI Processor architecture enables training deep learning models, while containing operational costs.
In the live demo we will show you how to get started on Gaudi, review the software architecture and the developer resources to help you build new and migrate model training from existing architectures to Gaudi.
A live Q&A to follow.
Agenda
- Gaudi overview
- Cloud and datacenter solutions powered by Gaudi processors
- Software and developer tools
- Live demo
- Q&A
Featured speakers:
Sree Ganesan
Head of Software Products
Sree Ganesan leads Software Product Management at Habana Labs, working alongside a diverse global team to deliver state-of-the-art deep learning capabilities of the Habana SynapseAI® software suite to the market. Previously, she was Engineering Director in Intel’s AI Products Group, where she was responsible for AI software strategy and deep learning framework integration for Nervana NNP AI accelerators.
Yuting Yang
Habana Deep Learning Training Team
Yuting Yang manages the deep learning training team in the Application Engineering organization at Habana Labs. He was the engineering manager in Intel’s AI Products Group, responsible for distributed training using Nervana NNP AI accelerators. Prior to AI, Yuting worked for Intel GPU, spanning 3D graphics, media, and GPGPU.