Fundamentals of Deep Learning (NVIDIA DLI certification)

Tuesday 21 Oct 2025, 09:00 → 17:00 Europe/Berlin

Hörsaal (D2)

 

The Max‑Planck Computing and Data Facility (MPCDF), in partnership with NVIDIA, is pleased to invite you to a one‑day, on-site only, hands‑on Deep Learning workshop.

 

This NVIDIA Deep Learning Institute (DLI) course provides a comprehensive, hands-on introduction to the fundamentals of deep learning. Through practical exercises, you will train neural networks from the ground up for both computer vision and natural language processing applications. You’ll gain experience with essential tools and techniques to enhance model performance, and discover how to efficiently apply cutting-edge, pre-trained models to accelerate your own projects. By successfully completing the final assessment, you will earn an NVIDIA DLI certificate, demonstrating your proficiency in the foundational concepts and practical skills of deep learning.

 

 

Learning Objectives

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

Topics Covered

• PyTorch
• Convolutional Neural Networks (CNNS)
• Data Augmentation
• Transfer Learning
• Natural Language Processing

Prerequisites

An understanding of fundamental programming concepts in Python 3, such as functions, loops, dictionaries, and arrays; familiarity with Pandas data structures; and an understanding of how to compute a regression line.

Hardware Requirements

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

How to Apply:

Please submit your application by Thursday, 16 October 2025, using the link provided in the email or contact the organizers. 

Participation is limited to the first 50 applicants, so we encourage you to apply promptly.

Contacts:

If you have any questions about the workshop or the application process, feel free to contact us:

• piero.coronica@mpcdf.mpg.de
• nastassya.horlava@mpcdf.mpg.de

1 Introduction

1. Meet the instructor.
2. Create an account at courses.nvidia.com/join

2 The Mechanics of Deep Learning

Explore the fundamental mechanics and tools involved in successfully training deep neural networks:

1. Train your first computer vision model to learn the process of training.
2. Introduce convolutional neural networks to improve accuracy of predictions in vision applications.
3. Apply data augmentation to enhance a dataset and improve model generalization.

12:30 Lunch Break

3 Pre-trained Models and Large Language Models

Leverage pre-trained models to solve deep learning challenges quickly. Train recurrent neural networks on sequential data:

1. Integrate a pre-trained image classification model to create an * automatic doggy door.
2. Leverage transfer learning to create a personalized doggy door that only lets in your dog.
3. Use a Large Language Model (LLM) to answer questions based on provided text.

15:00 Break

4 Final Project: Object Classification

Apply computer vision to create a model that distinguishes between fresh and rotten fruit:

1. Create and train a model that interprets color images.
2. Build a data generator to make the most out of small datasets.
3. Improve training speed by combining transfer learning and feature extraction.
4. Discuss advanced neural network architectures and recent areas of research where students can further improve their skills.

5 Final Review

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