NVIDIA DLI Fundamentals of Deep Learning

A comprehensive 8-hour instructor-led training that introduces participants to deep learning techniques, focusing on computer vision and natural language processing. Learn fundamental deep learning training techniques using PyTorch through hands-on exercises with dedicated GPU-accelerated cloud server access.

Key Topics Covered:

• Mechanics of deep learning
• Convolutional neural networks
• Data augmentation techniques
• Pre-trained models and transfer learning
• Image classification

Learning Objectives:

• Learn fundamental deep learning training techniques
• Understand common data types and model architectures
• Enhance datasets through data augmentation
• Leverage transfer learning between models to achieve efficient results with less data and computation
• Build confidence in deep learning frameworks

Prerequisites:

NVIDIA DLI Generative AI with Diffusion Models

About this Course

Thanks to improvements in computing power and scientific theory, generative AI is more accessible than ever before. Generative AI plays a significant role across industries due to its numerous applications, such as creative content generation, data augmentation, simulation and planning, anomaly detection, drug discovery, personalized recommendations, and more. In this course, learners will take a deeper dive into denoising diffusion models, which are a popular choice for text-to-image pipelines.

NVIDIA DLI Building AI Agents with Multimodal Models

About this Course

Learn how to build neural network agents that reason across multiple data types using advanced fusion techniques, OCR, and NVIDIA AI Blueprints for real-world applications like robotics and video search and summarization.

Learning Objectives

In this course, you will learn about:

• Different data types and how to make them neural network ready
• Model fusion, and the differences between early, late, and intermediate fusion
• PDF extraction using OCR
• The difference between modality and agent orchestration
• Customization of NVIDIA AI Blueprints with Video Search and Summarization (VSS)

Topics Covered

• Begin with a robotics use case to show how different datatypes impact an effective neural-networks architecture.
• Apply mathematical concepts from robotics to Large Language Models (LLMs) to modify them for non-language data input.
• End with orchestration of multiple models to answer user queries.

Course Outline

1. Early and Late Fusion (1 hr)

   [Read More]

Practical Computer Vision Bootcamp

A comprehensive, free and open-source computer vision learning path from foundational concepts to advanced applications. This hands-on bootcamp is designed for learners at various skill levels, from beginners to practitioners, focusing on practical implementation through Jupyter notebooks and real-world applications.

About this Course

This bootcamp provides a structured learning experience in computer vision, combining theoretical understanding with practical implementation. All materials are freely available on GitHub, making cutting-edge computer vision education accessible to everyone.