Applied Generative AI and Natural Language Processing

I am a hands-on Data Scientist with a lot of domain knowledge of Renewable Energies, especially Wind Energy.

Currently, I work for a leading manufacturer of wind turbines. I have provided training on Generative AI, Data Science, and Machine Learning with R and Python for many years.

I studied Aeronautics and Economics. My main interests are Machine Learning and Data Science.

Course Highlights:

• NLP-Introduction

  • Gain a solid understanding of the fundamental principles that govern Natural Language Processing and its applications.

  • Basics of NLP.

  • Word Embeddings.

  • Transformers.

• Apply Huggingface for Pre-Trained Networks

  • Learn about Huggingface models and how to apply them to your needs.

• Model Fine-Tuning

  • Sometimes pre-trained networks are not sufficient, so you need to fine-tune an existing model on your specific task and/or dataset. In this section, you will learn how.

• Vector Databases

  • Vector Databases make it simple to query information from texts. You will learn how they work and how to implement vector databases..

  • Tokenization.

  • Implement Vector DB with ChromaDB.

  • Multimodal Vector DB.

• OpenAI API

  • OpenAI with ChatGPT provides a very powerful tool for NLP. You will learn how to make use of it via Python and integrate it into your workflow.

• Prompt Engineering

  • Learn strategies to create efficient prompts.

• Advanced Prompt Engineering

  • Few-Shot Prompting.

  • Chain-of-Thought.

  • Self-Consistency Chain-of-Thought.

  • Prompt Chaining.

  • Reflection.

  • Tree-of-Thought.

  • Self-Feedback.

  • Self-Critique.

• Retrieval-Augmented Generation

  • RAG Theory.

  • Implement RAG.

• Capstone Project "Chatbot"

  • create a chatbot to "chat" with a PDF document.

  • create a web application for the chatbot.

• Open Source LLMs

  • learn how to use OpenSource LLMs.

  • Meta Llama 2.

  • Mistral Mixtral.

• Data Augmentation

  • Theory and Approaches of NLP Data Augmentation.

  • Implementation of Data Augmentation.