Explore the fundamentals of deep learning by training neural networks and using results to improve performance and capabilities.

Learn how to build a variety of LLM-based applications through the use of modern prompt engineering techniques.

Learn how to build applications for a variety of language-related tasks using large language models.

Just like how humans have different networks in their brain in order to process multisensory information, multimodal models have an organized structure to optimize reasoning based on multiple input data types.

Learn how to perform multiple analysis tasks on large datasets using RAPIDS, a collection of data science libraries that allows end-to-end GPU acceleration for data science workflows.

Learn how to improve LLM application capabilities and reduce the size of required LLMs using parameter efficient fine-tuning (PEFT).

Learn how to design intelligent agents that can be adapted for arbitrary environments at scale. Utilizing frameworks like LangGraph and NVIDIA NIM, you'll build agents capable of deep thought, long-horizon reasoning, content management, and real-time operations.

Learn how to write, compile, and run GPU-accelerated code, leverage NVIDIA® CUDA® core libraries to harness the power of massive parallelism provided by modern GPU accelerators, optimize memory migration between CPU and GPU, and implement your own algorithms.

Learn how to move RAG systems from proof-of-concept to enterprise-grade deployments, focusing on scalability, auto-scaling, monitoring, and data management. The workshop will also feature NVIDIA NIM™ microservices for optimizing production-level performance.

Agents powered by large language models (LLMs) have shown great retrieval capability for using tools, looking at documents, and plan their approaches. This course will show you how to deploy an agent system in practice with the flexibility to scale up your system to meet the demands of your customers.