Intelligent Video Analytics (IVA) Deep Learning­

Posted on May 16, 2017 |  

 

About the Event

Ready to transform your everyday video into valuable insight and decision-making?

NVIDIA Intelligent Video Analytics (IVA) makes it easy for companies to create robust security and surveillance solutions – from cameras to appliances to servers – using the power of deep learning.

The session is especially useful for companies to boost sales, increase customer satisfaction, lower theft, and boost public safety. This session will cover the advanced topics of Deep Learning, including IVA application development methods, optimization techniques, Deep Neural Networks (DNN) training and deployment environment recommendations.

The course is suitable for developers, engineers and data scientists who would like to learn more and get trained on optimizing and deploying neural networks to solve real-world problems via video analytics, security and surveillance disciplines.


Key Takeaways

Acquire knowledge on Deep Neural Networks (DNN) techniques within the deep learning workflow to solve a real-world video analytics problems

Learn how to use Tensor RT to optimize developed DNN

Learn about general optimization technique of IVA algorithm on GPUs

Learn about INT8 for DNN optimization knowledge and techniques

·   Learn about GPU multi-thread safe application & management techniques


Our Speaker

Leo Liao is IVA expert at NVIDIA, APAC and Deep Learning practitioner and has over 10 years of experience in computer vision/NLP and modern machine learning techniques. He graduated from the National Taiwan University.


Agenda

08:30AM – 09:00AM : Registration

09:00AM – 10:00AM : Deep Learning Techniques & Tensor RT 2.0, and Enhancement

10:00AM – 10:15AM: Break

10:15AM – 11:45AM : Optimization Technique and INT8 Technique

11:45AM – 12:00PM : Break

12:00PM – 1:00PM : CPU part of Memory Pooling & Camera stream optimization technique

1:00PM – 2:00PM : Break  

2:00PM – 3:30PM : GPU Multi-thread safe application & Management Technique

3:30PM – 3:45PM :  Break

3:45PM – 4:45PM : Profiling & Debugging

4:45PM : End


Session Requirements

Please bring your laptop to participate in hands-on exercises. A GPU in your laptop is not required.

No previous GPU programming experience is required for the hands-on. However, beginner-level C and Linux experience will be expected.

To familiarize yourself with the course, we would recommend to watch a few short (approx. 5 min) YouTube videos on introductory GPU programming topics.

These CUDACasts can be found here.  Also, please take time to register at our CUDA developer for more updates and information.


Registration Fees, Cancellation and Refund

The session fee is RM100

Participant can make the payment via the online registration page.

Cancellation of registration and full refund are only allowed within 48 hours prior to the program. Any cancellations received less than 48 hours will not be refunded.

Blue Ocean Strategy (BOS) For Startups

May 09, 2015 1 day   Closed

Blue Ocean Strategy (BOS) For Startups

Blue ocean means an untapped, not ventured, competitor free market space. It is also a…

The Arc Of An Idea Series

Oct 03, 2015 — Dec 05, 2015 6 Weeks   Closed

The Arc Of An Idea Series

This workshop will provide a series of lectures which will encompass the entire life cycle…

IP Essentials for Startups (Protecting your Inventions, Business, and Brand)

Oct 06, 2015 1 Day   Closed

IP Essentials for Startups (Protecting your Inventions, Business, and Brand)

This program covers the basics of what intellectual property is, and why every startup or…

Get Yourself Digitally Qualified And A Job Series

Oct 17, 2015 — Dec 19, 2015 6 weeks   Closed

Get Yourself Digitally Qualified And A Job Series

If you are new to Google AdWords or would like to refresh your fundamentals knowledge,…



Keep up to date with the startup ecosystem. Subscribe to our mailing list.

By clicking 'Subscribe' I accept the Terms of Use and Privacy Policy