21. Lipanj 2019 - 20:30 do 23:30
Podijelite ga na:

NVIDIA Deep Learning Institute Fundamentals of Deep Learning Workshop | FESB | Petak, 21. Lipanj 2019

The NVIDIA Deep Learning Institute (DLI) and Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture invite you to attend a hands-on deep learning workshop on 21. 06. 2019. from 8:30 – 16:30 at the Faculty, exclusively for verifiable academic students, staff, and researchers.
NVIDIA DLI offers hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning and accelerated computing.
This workshop will be delivered by Prof. Dubravko Culibrk, who is an NVIDIA University Ambassador.  
About This Workshop:This workshop teaches deep learning techniques for a range of computer vision tasks through a series of hands-on exercises. You will work with widely-used deep learning tools, frameworks, and workflows to train and deploy neural network models on a fully-configured, GPU-accelerated workstation in the cloud. After a quick introduction to deep learning, you will advance to: building and deploying deep learning applications for image classification and object detection, modifying your neural networks to improve their accuracy and performance, and implementing the workflow you have learned on a final project. At the end of the workshop, you will have access to additional resources to create new deep learning applications on your own.
Workshop Agenda:




(45 mins)

Course overviewGetting started with deep learning

Introduction to deep learning, situations in which it is useful, key terminology, industry trends, and challenges

Break (15 mins)



Unlocking New Capabilities
(120 mins)

Biological inspiration for deep neural networks (DNNs)Training DNNs with big data

Hands-on exercise: training neural networks to perform image classification by harnessing the three main ingredients of deep learning: deep neural networks, big data, and the GPU

Break (45 mins)



Unlocking New Capabilities
(40 mins)

Deploying DNN models

Hands-on exercise: deployment of trained neural networks from their training environment into real applications

Measuring and Improving Performance
(100 mins)

Optimizing DNN performance 
Incorporating object detection

Hands-on exercise: neural network performance optimization and applying DNNs to object detection

(20 mins)

Summary of key learnings

Review of concepts and practical takeaways

Break (15 mins)



(60 mins)

Assessment project: train and deploy a deep neural network

Validate learnings by applying the deep learning application development workflow (load dataset, train and deploy model) to a new problem

Next Steps
(15 mins)

Workshop survey
Setting up your own
GPU-enabled environment
Additional project ideas

Learn how to setup your GPU-enabled environment to begin work on your own projects. Explore additional project ideas along with resources to get started with NVIDIA AMI on the cloud, nvidia-docker, and the NVIDIA DIGITS container.

Familiarity with programming fundamentals such as functions and variables.
Workshop Setup Instructions:
 1.      Create an NVIDIA Developer account at .
2.      Make sure that WebSockets works for you:
·        Test your laptop at
·        Under ENVIRONMENT, confirm that “WebSockets” is checked yes.
·        Under WEBSOCKETS (PORT 80), confirm that “Data Receive,” “Send,” and “Echo Test” are checked yes.
3.      If there are issues with WebSockets, try updating your browser. We recommend Chrome, Firefox, or Safari for an optimal performance.
4.      Once onsite, visit and enter the event code provided by the instructor.