NVIDIA GTC starts on April 12th with more than 1,400 sessions including the latest deep learning technologies in conversational AI, recommender systems, computer vision, and video streaming.
Here’s a preview of some of the top AI/DL sessions at GTC.
- Building and Deploying a Custom Conversational AI App with NVIDIA Transfer Learning Toolkit and Riva
Tailoring the deep learning models in a conversational AI pipeline to the needs of your enterprise is time-consuming. Deployment for a domain-specific application typically requires several cycles of re-training, fine-tuning, and deploying the model until it satisfies the requirements. In this session, we will walk you through the process of customizing ASR and NLP pipelines to build a truly customized, production-ready conversational AI application that is fine-tuned to your domain.
Arun Venkatesan, Product Manager, Deep Learning Software, NVIDIA
Nikhil Srihari, Deep Learning Software Technical Marketing Engineer, NVIDIA
- Accelerated ETL, Training and Inference of Recommender Systems on the GPU with Merlin, HugeCTR, NVTabular, and Triton
In this talk we’ll share the Merlin framework, consisting of NVTabular for ETL, HugeCTR for training, and Triton for inference serving. Merlin accelerates recommender systems on GPU, speeding up common ETL tasks, training of models, and inference serving by ~10x over commonly used methods. Beyond providing better performance, these libraries are also designed to be easy to use and integrate with existing recommendation pipelines.
Even Oldridge, Senior Manager, Recommender Systems Framework Team, NVIDIA
- Accelerating AI Workflows with NGC
This session will walk through building a conversational AI solution using the artifacts from the NGC catalog, including a Jupyter notebook, so the process can be repeated offline. It will also cover the benefits of using NGC software throughout AI development journeys.
Adel El Hallak, Director of Product Management for NGC, NVIDIA
Chris Parsons, Product Manager, NGC, NVIDIA
- NVIDIA Maxine: An Accelerated Platform SDK for Developers of Video Conferencing Services
Connect with experts in this session to learn about the latest updates to NVIDIA Maxine, such as how applications based on Maxine can reduce video bandwidth usage down to one-tenth of H.264 using AI video compression. Also see the latest innovations from NVIDIA research, such as face alignment, gaze correction, face re-lighting and real-time translation, in addition to capabilities such as super-resolution, noise removal, closed captioning and virtual assistants.
Davide Onofrio, Technical Marketing Engineer Lead, NVIDIA
Abhijit Patait, Director, System Software, NVIDIA
Abhishek Sawarkar, Deep Learning Software Technical Marketing Engineer, NVIDIA
Tanay Varshney, Technical Marketing Engineer, Deep Learning, NVIDIA
Alex Qi, Product Manager, AI Software, NVIDIA
- Easily Deploy AI Deep Learning Models at Scale with Triton Inference Server
Triton Inference Server is a model serving software that simplifies the deployment of AI models at scale in production. It’s an open-source serving software that lets teams deploy trained AI models from any framework on any GPU- or CPU-based infrastructure. Learn about high performance inference serving with Triton’s concurrent execution, dynamic batching, and integrations with Kubernetes and other tools.
Mahan Salehi, Deep Learning Software Product Manager, NVIDIA