[HYBRID] Fundamentals of Deep Learning

Wednesday 17 May 2023, 08:45 → 17:00 Europe/Prague

Meeting room Konrad (HYBRID)

Annotation

Businesses worldwide use artificial intelligence (AI) to solve their greatest challenges. Healthcare professionals use AI to enable more accurate, faster diagnoses of patients. Retail businesses use it to offer personalised customer shopping experiences. Automakers use it to make personal vehicles, shared mobility, and delivery services safer and more efficient. Deep learning is a powerful AI approach that uses multi-layered artificial neural networks to deliver state-of-the-art accuracy in object detection, speech recognition, and language translation tasks. Using deep learning, computers can learn and recognise patterns from data considered too complex or subtle for expert-written software.

In this workshop, you’ll learn how deep learning works through hands-on exercises in computer vision and natural language processing. You’ll train deep learning models from scratch, learning tools and tricks to achieve highly accurate results. You’ll also learn to leverage freely available, state-of-the-art pre-trained models to save time and get your deep learning application up and running quickly.

Learning Objectives

By participating in this workshop, you’ll:

• Learn the fundamental techniques and tools required to train a deep-learning model
• Gain experience with common deep-learning data types and model architectures
• Enhance datasets through data augmentation to improve model accuracy
• Leverage transfer learning between models to achieve efficient results with fewer data and computation
• Build confidence to take on your project with a modern deep-learning framework

Level

beginner

Language

English

Prerequisites

An understanding of fundamental programming concepts in Python, such as functions, loops, dictionaries, and arrays.

Hardware requirements

Desktop or laptop computer capable of running the latest version of Chrome or Firefox. Each participant will be provided with dedicated access to a fully configured, GPU-accelerated workstation in the cloud.

Tools, libraries, and frameworks

Tensorflow, Keras, Pandas, NumPy

Tutor

Georg Zitzlsberger is a research specialist for Machine and Deep Learning at IT4Innovations. For over four years, he has been certified by NVIDIA as a University Ambassador of the NVIDIA Deep Learning Institute (DLI) program. This certification allows him to offer NVIDIA DLI courses to users of IT4Innovations' HPC services. In addition, in collaboration with Bayncore, he was a trainer for Intel HPC and AI workshops and conferences across Europe. He has been contributing to these events, which are held for audiences from industry and academia, for five years. Recently, he also received instructor certifications from Intel for oneAPI related courses.

 

Certificate

Upon completing the assessment, participants will receive an NVIDIA DLI certificate to recognise their subject matter competency and support professional career growth.

Practicalities

This training will be a hybrid event. Technical details about joining will be sent to the accepted registrants before the event. If you are coming to IT4Innovations to attend personally, please bring your laptop.

Please note that the training is held using Zoom. We advise all participants to download the Zoom application to enjoy full functionality. The link to the Zoom meeting will be sent only to registered participants.

The capacity is limited to 30 participants combined online and onsite.

Price Information

Full price per person: 10 000 CZK

Subsidized price: 1 500 CZK

Terms of subsidy and cancellation

 

Registration

 

 

 

 

Terms of the subsidy and cancellation policy.pdf

Introduction

The mechanics of Deep Learning

10:30 Coffee Break

The Mechanics of Deep Learning - Hands-on

12:00 Lunch Break

Pre-trained Models with Hands-on

14:45 Coffee Break

Advanced Architectures: Recurrent Networks with Hands-on

Wrap Up and Assesment