1. Home
  2. Program
  3. Tutorials
  4. Violeta Holmes

Violeta Holmes
Fundamentals of Deep Learning for Computer Vision

Tutorial will be held on 27th of August. Number of participants is limited, please express your interest sending e-mail to mira@dmi.uns.ac.rs.


Abstract: This tutorial teaches deep learning techniques for a range of computer vision tasks. After an introduction to deep learning, you’ll 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 techniques you’ve learned on a final project. At the end of the workshop, you’ll have access to additional resources to create new deep learning applications on your own.

Assesment type: Code-based
Certificate:

Upon successful completion of the assessment, participants will receive an NVIDIA DLI certificate to recognize their subject matter competency and support professional career growth.
Prerequisites:

Familiarity with programming fundamentals

Tools, libraries, and frameworks:

Caffe, DIGITS


Learning Objectives:
  • Implement common deep learning workflows, such as image classification and object detection
  • Experiment with data, training parameters, network structure, and other strategies to increase performance and capability of neural networks
  • Integrate and deploy neural networks in your own applications to start solving sophisticated real-world problems

Agenda:


TOPIC DESCRIPTION

Introduction

(15 mins)
  • Meet the instructor.
  • Create an account at courses.nvidia.com/join

Unlocking New Capabilities

(120 mins)
  • Learn the biological inspiration behind deep neural networks (DNNs).
  • Explore training DNNs with big data.
  • Train neural networks to perform image classification by harnessing the three main ingredients of deep learning: deep neural networks, big data, and the GPU.

Break

(60 mins)

Unlocking New Capabilities

and Measuring and

Improving Performance

(120 mins)
  • Deploy trained neural networks from their training environment into real applications.
  • Optimize DNN performance.
  • Incorporate object detection into your DNNs.

Final Project

(120 mins)
  • Validate learnings by applying the deep learning application development workflow (load dataset, train, and deploy model) to a new problem.
  • Learn how to set up your GPU-enabled environment to begin work on your own projects.
  • Explore additional project ideas and resources to get started with NVIDIA AMI in the cloud, nvidia-docker, and the NVIDIA DIGITS container.

Final Review

(15 mins)
  • Review key learnings and wrap up questions.
  • Complete the assessment to earn a certificate.
  • Take the workshop survey.


Biographical note: Violeta Holmes is a Reader (Associate Professor) in High Performance Computing at Huddersfield University with over 25 years of teaching and research experience in computing and engineering, and (co)author of over 100 publications in refereed journals and international conferences.

She is High-Performance Computing (HPC) Research group Leader at the University of Huddersfield, ARCHER UK National Supercomputing Service champion, NVIDIA Deep Learning Institute (DLI) certified instructor and ambassador.

Violeta is actively promoting partnership between industry and academia working closely with local SMEs. She has led and participated in UK government and university funded research projects. She has presented her work at UK government events and scientific conferences on Higher Education and High Performance Computing, and she promotes UK education through British Council activities.

As a Chartered Engineer and a member of the Institute of Engineering and Technology, and BSC The Chartered Institute for IT, she continues to support the advancement and promotion of the careers of women in science, engineering and technology in Higher Education and research.

NEWS