Learning Sprint: GenAI and LLMs

For whom?

• Data engineers, data architects, developers, technical project managers, product owners and other technical and IT roles

Why?

• To better understand and use GenAI technologies
• To engage in practical skill development and become more confident
• To combine theory with practical use cases
• To network with like-minded people and solve interesting problems together

Sign up on a a cohort-based online Learning Sprint including

• 3 x 5 min tutorial videos to help you become aware
• Pre-tasks to solve before workshop sessions
• 3 x 2,5h Learning Sprint + 2h retrospective workshop (within one week)
• Total time spent on learning is approximately 2 days
• Focus is on GenAI and natural language processing (image and video excluded)

How?

• Highly practical social learning experience with 5 projects altogether (3 pre-tasks)
• Three online coaching sessions focus on discussing the tutorial videos and the pre-tasks
• An interactive, hands-on problem-solving Sprint with feedback from the coach

What?

In this Learning Sprint participants will:

• learn about the core principles of Machine Learning, different paradigms for learning from data, as well as an introduction to Deep Learning and Neural Networks.
• look into the architecture of LLMs, including the Transformer architecture, and practical skills in text generation techniques like sampling and decoding.
• gain expertise in prompt engineering, learning how to craft effective prompts for different tasks and understanding advanced techniques like zero-shot, one-shot, and few-shot prompting.
• address the potential risks associated with Generative AI systems, such as biases and hallucinations, quality and reliability concerns, and inference cost and latency.
• apply LLMs in various industry use cases, customize and fine-tune models for specific applications, and grasp the concepts of model chaining and defensive UX for robust applications.
• evaluate LLM systems using both quantitative and qualitative metrics, and will learn how to monitor, audit, and debug LLM outputs to ensure quality and reliability.
• engage in practical labs and exercises that allow them to apply their knowledge, such as prompt engineering, output analysis, fine-tuning LLMs, and implementing RAG systems, ensuring that theoretical knowledge is solidified through direct application.