NVIDIA DLI Deep Learning Fundamentals Instructor-Led

jeudi 5 nov. 2020, 08:30 → 17:30 Europe/Paris

Virtual Classroom

The NVIDIA Deep Learning Institute (DLI) trains developers, data scientists, and researchers on how to use deep learning and accelerated computing to solve real-world problems across a wide range of domains.

With access to GPU-accelerated workstations in the cloud, you’ll learn how to train, optimize, and deploy neural networks using the latest deep learning tools, frameworks, and SDKs. You’ll also learn how to assess, parallelize, optimize, and deploy GPU-accelerated computing applications.

Businesses worldwide are using artificial intelligence (AI) to solve their greatest challenges. Healthcare professionals use AI to enable more accurate, faster diagnoses in patients. Retail businesses use it to offer personalized customer shopping experiences. Automakers use AI to make personal vehicles, shared mobility, and delivery services safer and more efficient. Deep learning is a powerful approach to implementing AI that uses multi-layered artificial neural networks to deliver state-of-the-art accuracy in tasks such as object detection, speech recognition, and language translation. Using deep learning, computers are now able to learn and recognize patterns from data that are 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 will 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 today.

By participating in this is workshop you will:

• Practice 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 less data and computation
• Build confidence to take on your own project with a modern, deep learning framework

Prerequisites: Understanding of fundamental programming concepts in Python such as functions, loops,dictionaries, and arrays.

Tools, libraries, and frameworks: Tensorflow, Keras, Pandas, Numpy

Fundamentals of Deep Learning https://www.nvidia.com/content/dam/en-zz/Solutions/deep-learning/deep-learning-education/dli-fundamentals-of-deep-learning-1369828-r3-web.pdf

Steps to complete prior to getting started

1. Create or log into your NVIDIA Developer Program account.
2. Make sure WebSockets works for you. Visit websocketstest.courses.nvidia.com and make sure all three test steps are checked yes. If there are issues, try updating your browser.
   • Note, only Chrome or Firefox is supported.
3. Please test your system / audio by clicking on the following link. We highly recommend the use of headsets to get the best audio quality possible and to limit background noise and feedback. If you experience webcam or audio problems, go to here for resolution. Systems problems will likely either require upgrading your browser or pertain to problems with your internet connection. You will be responsible for resolving these issues.

08:30 Introduction

Meet the instructor

1 The Mechanics of Deep Learning

Explore the fundamental mechanics and tools involved in successfully training deep neural networks: - Train your first computer vision model to learn the process of training - Introduce convolutional neural networks to improve accuracy of predictions in vision applications. - Apply data augmentation to enhance a dataset and improve model generalization.

Orateur: Abubakrelsedik Karali (NVIDIA DLI)

11:45 Lunch Break

2 Pre-trained Models and Recurrent Networks

Leverage pre-trained models to solve deep learning challenges quickly. Train recurrent neural networks on sequential data : - Integrate a pre-trained image classification model to create an automatic doggy door. - Leverage transfer learning to create a personalized doggy door that only lets in your dog. - Train a model to autocomplete text based on New York Times headlines.

Orateur: Abubakrelsedik Karali (NVIDIA DLI)

15:00 Break

3 Final Project : Object Classification

Apply computer vision to create a model that distinguishes between fresh and rotten fruit. - Create and train a model that interprets color images. - Build a data generator to make the most out of small datasets. - Improve training speed by combining transfer learning and feature extraction. - Discuss advanced neural network architectures and recent areas of research where students can further improve their skills.

Orateur: Abubakrelsedik Karali (NVIDIA DLI)

4 Final Review

- Review key learnings and answer questions. - Complete the assessment and earn a certificate. - Complete the workshop survey. - Learn how to set up your own AI application development environment.