Building Video AI Applications

 

About this Course

AI-based video understanding can unlock insights, whether it’s recognizing a cat in your backyard or optimizing customers’ shopping experiences. The NVIDIA Jetson Nano Developer Kit is an easy-to-use, powerful computer that lets you run multiple neural networks in parallel. This makes it a great platform for an introduction to intelligent video analytics (IVA) applications using the NVIDIA DeepStream SDK. In this course, you'll use JupyterLab notebooks and Python application samples on your Jetson Nano to build new projects that extract meaningful insights from video streams through deep learning video analytics. The techniques you learn from this course can then be applied to your own projects in the future on the Nano or other Jetson platforms at the Edge.

Learning Objectives

You'll learn how to:

Set up your Jetson Nano

Build end-to-end DeepStream pipelines to convert raw video input into insightful annotated video output

Build alternate input and output sources into your pipeline

Configure multiple video streams simultaneously

Configure alternate inference engines such as YOLO

Upon completion, you'll be able to build DeepStream applications that annotate video streams from various and multiple sources to identify and classify objects, count objects in a crowded scene, and output the result as a live stream or file.

Topics Covered

Tools, libraries, frameworks used in this course include DeepStream, TensorRT, Jetson Nano, and Python

Course Outline

1. Setting up your Jetson Nano

Step-by-step guide to set up your hardware and software for the course projects

Note: This course supports the NVIDIA Jetson Nano Developer Kit but does not support the NVIDIA Jetson Orin Nano Developer Kit

• Introduction and Setup

Video walk-through and instructions for setting up JetPack and what items you need to get started

• Camera Setup

How to connect your camera to the Jetson Nano Developer Kit

• Headless Device Mode

Video walk-through and instructions for running the Docker container for the course using headless device mode (remotely from your computer).

• JupyterLab

A brief introduction to the JupyterLab interface and notebooks

• Media Player

How to set up video streaming on your computer

2. Introduction to DeepStream SDK

Overview of key DeepStream SDK features and important reference links for deeper exploration

• What is the DeepStream SDK?

An overview of DeepStream applications and the DeepStream SDK

• GStreamer Plugins

Introduction to the GStreamer framework and plugins

• TensorRT

Introduction to TensorRT

• Video to Analytics With the DeepStream SDK

Outline of the DeepStream metadata structure

3. Exploring DeepStream SDK

Course notebook and environment details for your Jetson Nano hands-on learning experience

• Build DeepStream Applications

Instructions for opening the first notebook in JupyterLab on Jetson Nano

• Exercises

A summary of the lesson notebooks included in the Jetson Nano MicroSD card image.

• Directory Structure

A summary of the DeepStream SDK directory structure

Free Courses : Building Video AI Applications

Read More

Building RAG Agents with LLMs

 

About this Course

The evolution and adoption of large language models (LLMs) have been nothing short of revolutionary, with retrieval-based systems at the forefront of this technological leap. These models are not just tools for automation; they are partners in enhancing productivity, capable of holding informed conversations by interacting with a vast array of tools and documents. This course is designed for those eager to explore the potential of these systems, focusing on practical deployment and the efficient implementation required to manage the considerable demands of both users and deep learning models. As we delve into the intricacies of LLMs, participants will gain insights into advanced orchestration techniques that include internal reasoning, dialog management, and effective tooling strategies.

Learning Objectives

The goal of the course is to teach participants how to:

Compose an LLM system that can interact predictably with a user by leveraging internal and external reasoning components.

Design a dialog management and document reasoning system that maintains state and coerces information into structured formats.

Leverage embedding models for efficient similarity queries for content retrieval and dialog guardrailing.

Implement, modularize, and evaluate a RAG agent that can answer questions about the research papers in its dataset without any fine-tuning.

By the end of this workshop, participants will have a solid understanding of RAG agents and the tools necessary to develop their own LLM applications.

Topics Covered

The workshop includes topics such as LLM Inference Interfaces, Pipeline Design with LangChain, Gradio, and LangServe, Dialog Management with Running States, Working with Documents, Embeddings for Semantic Similarity and Guardrailing, and Vector Stores for RAG Agents. Each of these sections is designed to equip participants with the knowledge and skills necessary to develop and deploy advanced LLM systems effectively.

Course Outline

Introduction to the workshop and setting up the environment.

Exploration of LLM inference interfaces and microservices.

Designing LLM pipelines using LangChain, Gradio, and LangServe.

Managing dialog states and integrating knowledge extraction.

Strategies for working with long-form documents.

Utilizing embeddings for semantic similarity and guardrailing.

Implementing vector stores for efficient document retrieval.

Evaluation, assessment, and certification.

Free Courses : Building RAG agents with LLMs

Read More

Augment your LLM Using Retrieval Augmented Generation

 

About this Course

Retrieval Augmented Generation (RAG) - Introduced by Facebook AI Research in 2020, is an architecture used to optimize the output of an LLM with dynamic, domain specific data without the need of retraining the model. RAG is an end-to-end architecture that combines an information retrieval component with a response generator. In this introduction we provide a starting point using components we at NVIDIA have used internally. This workflow will jumpstart you on your LLM and RAG journey.

What is RAG?

Retrieval Augmented Generation (RAG) is an architecture that fuses two powerful capabilities:

Information retrieval (like a search engine)

Text generation (using an LLM)

Instead of relying solely on a model’s pre-trained knowledge, RAG retrieves external, real-time or domain-specific information and injects it into the prompt. This results in:

• More accurate and up-to-date responses
• Customization to private/internal knowledge bases
• Better transparency and fact-grounding

Learning Objectives

By the end of this course, you will be able to:

Explain the Concept of Retrieval Augmented Generation (RAG):

Understand how RAG enhances LLM outputs by integrating external data sources during inference.

Describe the Components of a RAG Pipeline:

Break down the key stages—retrieval, prompt construction, and generation—and how they interact.

Implement a Simple RAG Workflow:

Build a working prototype that indexes documents, performs semantic search, and feeds relevant context to a language model for generation.

Use Open-Source Tools for RAG:

Get hands-on with libraries such as FAISS, Hugging Face Transformers, and simple vector stores to create a full retrieval-to-generation loop.

Evaluate the Benefits and Limitations of RAG:

Assess use cases where RAG is most effective, and understand its trade-offs (e.g., latency, relevance, hallucination reduction).

Topics Covered

Introduction to RAG

• What is Retrieval Augmented Generation?
• Why use it with LLMs?

RAG Architecture Overview

• Separation of retrieval and generation
• Benefits over pure LLM prompting

Data Indexing and Retrieval

• Creating vector embeddings
• Using FAISS or similar vector stores
• Semantic search vs keyword search

Prompt Augmentation

• Injecting retrieved documents into prompts
• Context window management

LLM Integration

• Feeding augmented prompts into LLMs
• Generating responses with grounded context

Hands-On Lab: Build a RAG Pipeline

• Index a document set
• Perform retrieval
• Generate RAG responses

In the age of LLMs, accuracy, context, and traceability matter more than ever. RAG enables smarter, leaner, and more trustworthy AI—especially in enterprise and mission-critical applications.

With this course, NVIDIA DLI has created one of the most accessible and practical introductions to RAG currently available. It’s short, impactful, and leaves you with working code and a real-world understanding of how to augment your AI with knowledge.

Free Courses : Augment your LLM using RAG

Read More

Building A Brain in 10 Minutes

 

About this Course

"Building a Brain in 10 Minutes" is a beginner-friendly course by NVIDIA’s Deep Learning Institute that gives you a hands-on introduction to how neural networks work—no prior experience or setup required. In just minutes, you'll build a simple neural network using TensorFlow 2, understand how data flows through neurons, and see how models learn through training. It's the perfect fast-track for anyone curious about AI and deep learning.

Learning Objectives

The goals of this exercise include:

• Exploring how neural networks use data to learn.
• Understanding the math behind a neuron.

Core Topics Covered 

AI Data: Learn how input data is formatted, normalized, and prepared for neural network training.

Neurons: Discover how each artificial neuron applies weights, biases, and activation functions to make decisions.

TensorFlow 2: Get familiar with defining simple models, running forward passes, computing loss, and updating weights through backpropagation.

Why This Course Shines

Speed to Insight: In just minutes, you go from zero to a functioning neural unit—perfect for quick learners or busy professionals.

Concrete Understanding: Rather than abstract theory, you see and modify the network yourself, reinforcing how data transforms at each layer.

Gateway to More: Once you grasp a single neuron, you're ready for deeper courses—like NVIDIA’s more advanced offerings on image classification, transformers, model parallelism, and CUDA-accelerated training.

“Building a Brain in 10 Minutes” is a crisp, effective, and motivating introduction to deep learning. You’ll walk away with not just knowledge, but a working neural network you built yourself—a solid foundation to explore more complex AI topics confidently.

Free Courses : Building a Brain in 10 Minutes

Read More

Introduction to Networking

Introduction to Networking: Free Course by NVIDIA on Coursera

In today's digital age, networking plays a pivotal role in connecting people, devices, and systems across the globe. Whether you're a tech enthusiast, a student, or a professional looking to upskill, understanding the fundamentals of networking is essential. NVIDIA, a global leader in AI and accelerated computing, offers a free course on networking .This course is designed to help learners grasp the core concepts of networking and apply them in real-world scenarios.

Why Learn Networking?

Networking is the backbone of modern technology. From browsing the internet to enabling AI-driven applications, networks facilitate seamless communication and data transfer. Learning networking fundamentals empowers you to:

• Understand how devices communicate.

• Troubleshoot network-related issues.

• Build and maintain efficient networks.

• Enhance your career opportunities in IT, cybersecurity, and cloud computing.

What the Course Offers

The Introduction to Networking course by NVIDIA covers essential topics to build a strong foundation in networking. Here’s what you can expect:

1. Core Networking Concepts

Gain a deep understanding of:

• How data flows across networks.

• The role of IP addresses and protocols.

• Networking hardware like routers and switches.

2. Hands-On Learning

The course includes practical exercises and real-world scenarios to help you apply theoretical knowledge effectively.

3. Expert Insights

Learn from industry professionals with years of experience in networking and computing.

4. Flexibility and Accessibility

Since the course is offered on Coursera, you can learn at your own pace, making it ideal for busy professionals and students.

Who Should Enroll?

This course is perfect for:

• Beginners with no prior knowledge of networking.

• IT professionals seeking to refresh their networking skills.

• Students exploring a career in technology.

Benefits of Taking This Course

• Free Enrollment: Access world-class content without spending a dime.

• Certificate of Completion: Add a valuable credential to your resume.

• Industry-Relevant Skills: Equip yourself with knowledge that’s in demand in the job market.

Join Free: Introduction to Networking

Conclusion

Whether you're new to networking or looking to enhance your existing skills, NVIDIA’s Introduction to Networking course on Coursera offers a comprehensive and accessible way to learn. Take the first step toward mastering networking fundamentals and unlocking new career opportunities. Enroll today and start your journey into the fascinating world of networking!

Read More

The Fundamentals of RDMA Programming

The Fundamentals of RDMA Programming

The "Fundamentals of RDMA Programming" course offered by NVIDIA on Coursera focuses on teaching Remote Direct Memory Access (RDMA), a crucial technology for high-speed server-to-server communication. RDMA enables direct memory access between systems without involving the CPU, making it ideal for applications requiring high throughput and low latency, such as HPC (high-performance computing) and data centers.

The course covers RDMA basics, core components, operations, code examples, and connection management. Learners will gain skills in writing RDMA applications over InfiniBand and Ethernet, understanding data-path flows, and managing memory efficiently. By the end, participants will be proficient in developing RDMA-based applications.

The Fundamentals of RDMA Programming course on Coursera provides comprehensive training in Remote Direct Memory Access (RDMA), a technology that allows servers to access each other's memory directly, bypassing the CPU. 

RDMA Basics: Understanding the core concepts, such as memory regions, queues, and buffers.

InfiniBand and Ethernet: Learning how RDMA operates over different networking fabrics.

Programming with RDMA: Hands-on exercises on building RDMA-based applications.

Data Path Flows: Understanding how data is transferred with minimal CPU involvement.

The Fundamentals of RDMA Programming course on Coursera offers the following key highlights:

Key Highlights of the course:

Introduction to RDMA: Learn the core concepts of Remote Direct Memory Access, including its benefits for high-performance applications.

Networking Protocols: Understand RDMA protocols such as InfiniBand and RoCE (RDMA over Ethernet).

Memory Management: Master memory region registration, allocation, and how they affect performance.

Efficient Data Communication: Explore how RDMA enables direct memory access between systems, bypassing the CPU for faster data transfer.

Hands-on Exercises: Gain practical experience writing RDMA-based applications, managing connections, and optimizing network performance.

This course is designed to equip learners with the skills to develop efficient, low-latency applications in high-performance computing environments.

What you'll learn

• RDMA Basics: Bypassing the OS, Memory zero copy and transport offload
• Core RDMA:  RDMA verbs and objects, data-path flow and memory management
• RDMA Operations:  Send and receive operations, RDMA write and RDMA read operations, atomic operations
• Become familiar with InfiniBand architecture layer, RDMA basic flow, create a completion queue (CQ) and a queue pair (QP), and execute RDMA operation
•  Establish connection using RDMA_CM API

Future enhancements in RDMA programming may include:

Support for New Protocols: Expanding support for upcoming RDMA protocols like PCIe-based RDMA and advanced Ethernet technologies.

Integration with AI/ML Workloads: Optimizing RDMA for AI and machine learning environments, which require low latency and high-throughput communication.

Scalability Improvements: Increasing the scalability of RDMA in large-scale distributed systems.

Security Enhancements: Implementing better security features, like encryption, in RDMA communication to prevent data breaches in critical environments.

These developments could expand RDMA’s applications, making it even more powerful for modern high-performance computing systems.

Join Free: The Fundamentals of RDMA Programming

Conclusion:

The Fundamentals of RDMA Programming course provides essential knowledge and hands-on experience in building efficient, high-performance applications using RDMA. Through understanding RDMA protocols, memory management, and network communication, learners gain the skills to optimize data transfer processes. The course also equips professionals to work with technologies like InfiniBand and RoCE, making it a valuable resource for those seeking to enhance their expertise in high-performance computing and networking. As technology evolves, RDMA's role in low-latency, high-throughput systems will continue to grow.

Read More

AI Infrastructure and Operations Fundamentals

 

AI Infrastructure and Operations Fundamentals

The "AI Infrastructure and Operations Fundamentals" course by NVIDIA on Coursera is designed for IT professionals and those new to AI. It covers AI technologies, machine learning, deep learning, and the essential role of GPUs in AI workloads. The course provides insights into deploying AI infrastructure across various environments such as on-premises, cloud, and hybrid setups. With modules on AI operations and infrastructure management, it equips learners with the tools to support and manage AI workflows effectively. Completing this course also prepares you for the NVIDIA Certified Associate certification.

The AI Infrastructure and Operations Fundamentals course by NVIDIA on Coursera is a comprehensive learning experience aimed at IT professionals, engineers, and anyone looking to understand the foundational aspects of AI infrastructure. This course dives deep into how AI workloads are managed, optimized, and deployed across different environments, including on-premises, cloud, and hybrid setups.

Key highlights include:

Understanding AI infrastructure: Learn how GPUs power AI applications, and explore the deployment of AI systems.

Machine Learning and Deep Learning: Discover the crucial roles these technologies play in AI.

Practical skills: Learn best practices for infrastructure management and how to build efficient AI pipelines.

Certification: Completing this course can lead to the NVIDIA Certified Associate certification, enhancing your professional credibility in the AI space.

Ideal for those starting in AI or those working in operations and looking to expand their skill set, the course is designed to equip learners with the skills necessary to support AI workflows, optimize performance, and ensure smooth operations across AI infrastructures. Whether you're a beginner or already have some experience with AI, this course offers valuable insights into managing AI infrastructure efficiently.

What you'll learn

• Explore diverse applications of AI across various industries.
• Understand concepts like Machine Learning, Deep Leaning, training and inference.
• Trace the evolution of AI Technologies. From its inception to the revolutionary advances brought by Generative AI, and the role of GPUs.
• You will become familiar with deep learning frameworks and AI software stack.
• Learn about considerations when deploying AI workloads on a data center on prem, in the cloud, on a hybrid model, or on a multi-cloud environment.

The AI Infrastructure and Operations Fundamentals course by NVIDIA on Coursera is a valuable resource for those seeking to understand AI infrastructure management. It covers:

GPU-Powered AI: Learn about GPUs and their significance in accelerating AI and ML workloads.

Deployment Environments: Explore on-premise, cloud, and hybrid deployment strategies for AI systems.

AI Workflow Optimization: Gain practical skills in managing and optimizing AI pipelines for improved performance.

Scalability: Learn how to scale AI systems and ensure long-term efficiency.

Join Free: AI Infrastructure and Operations Fundamentals

Conclusion:

 This course is ideal for anyone looking to build or manage AI systems, with the added benefit of preparing learners for the NVIDIA Certified Associate certification, making it a great step forward in a tech career. The AI Infrastructure and Operations Fundamentals course by NVIDIA provides learners with essential skills to manage and deploy AI systems across various environments. By focusing on GPUs, AI workflows, and infrastructure optimization, it prepares professionals for AI infrastructure management and supports certification for the NVIDIA Certified Associate role. This course is perfect for those wanting to gain practical insights into AI operations and scale AI systems effectively, making it a strong foundation for a career in AI infrastructure

Read More

Introduction to Networking (Free Courses)

 

What you'll learn

You will learn what a network is and why it is needed.

Describe the network components and provide the requirements for a networking solution.

Introduce the OSI model and the TCP/IP protocol suite and their role in networking.

Cover the basics of Ethernet technology and understand how data is forwarded in an Ethernet network.

There are 2 modules in this course

Welcome to the Introduction to Networking Course. 

In this course we will cover the basics of networking, introduce commonly used TCP/IP protocols and cover the fundamentals of an Ethernet network. 

In addition, you’ll be equipped with the basic knowledge to understand the main data center requirements and how they can be fulfilled.

Upon successful completion of the course's final exam, you will receive a digital completion certificate that confirms your understanding of Ethernet technology basics and data forwarding within an Ethernet network.

Join Free: Introduction to Networking (Free Courses)

Read More