Getting Started with Generative AI

Overview

This course introduces the foundational concepts and advanced techniques in Generative AI, covering key topics such as model architectures, data preparation, prompt engineering, and deployment strategies. Learners will gain practical experience with cutting-edge tools and methodologies to effectively design, fine-tune, and deploy generative AI solutions.

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

- Define the core principles of generative AI, including models, algorithms, and applications. - Apply data pre-processing and vectorization techniques to enhance generative AI models. - Evaluate the strengths and weaknesses of GANs, autoencoders, transformers, and LLMs. - Analyze and optimize prompting techniques for improved model performance. - Design evaluation methods using metrics like BLEU and ROUGE to assess model outputs. This course is suitable for the aspiring AI practitioners, software developers, data scientists, and ML engineers who want to enhance their skills in building, deploying, and optimizing generative AI solutions.

Join us to establish a solid foundation in generative AI and take your career to the next level with hands-on expertise in this transformative technology!

Syllabus

• Foundations of Generative AI
This module introduces the fundamentals and advanced concepts of Generative AI, including its evolution, real-world applications, and key differences from discriminative models. Learners will explore data preprocessing, vectorization techniques like TF-IDF and Word2Vec, and gain hands-on experience with Autoencoders and GANs, enabling them to build and train generative models for AI-driven solutions.
• Transformer Models and Large Language Models (LLMs)
This module covers the fundamentals of attention mechanisms, the evolution of transformers, and major LLMs like GPT, PaLM, and LLaMA. It includes instruction-tuned models, API integration, and real-world applications. You’ll also explore the open-source LLM ecosystem, model comparisons, Hugging Face, and key ethical considerations.
• Generative AI Techniques and Tools
This module covers prompt engineering essentials, advanced prompting techniques like few-shot, zero-shot, and chain-of-thought, and strategies for optimizing generative AI outputs. You’ll learn how vector databases (ChromaDB, Pinecone, and Weaviate) enable semantic search and Retrieval-Augmented Generation (RAG). Hands-on work with LangChain shows how to build modular AI apps using prompt templates, tools, and agents for practical, state-of-the-art solutions.
• Fine-Tuning and Optimization of Generative Models
This module covers fine-tuning and optimizing generative models, including basics like data augmentation and hyperparameter tuning, and advanced methods such as PEFT, LoRA, and QLoRA for efficient adaptation. You’ll learn how to evaluate models using metrics like BLEU and ROUGE, balancing quantitative and qualitative assessments. The course also introduces building and deploying AI solutions with LLMOps and industry best practices for real-world use.
• Course Wrap-Up and Assessment
This module is designed to assess an individual on the various concepts and teachings covered in this course. Evaluate your knowledge with a comprehensive graded quiz, project, and labs.

---

Taught by

Edureka

---

Subjects

Computer Science