Generative AI is a form of artificial intelligence in which models are trained to generate new original content based on natural language input. Generative AI, such as ChatGPT and Dolly, has undoubtedly changed the technology landscape and unlocked transformational use cases, such as creating original content, generating code and expediting customer service. And the technology's applications are growing daily. Organizations that harness this transformative technology successfully will be differentiated in the market and be leaders in the future. Get up to speed on generative AI with this on-demand training.

Course Objectives:

• Define Generative AI
• Explain how Generative AI works
• Describe Generative AI Model Types
• Describe Generative AI Applications

• Deeply understand generative AI, describing the key steps in a typical LLM-based generative AI lifecycle, from data gathering and model selection, to performance evaluation and deployment
• Describe in detail the transformer architecture that powers LLMs, how they’re trained, and how fine-tuning enables LLMs to be adapted to a variety of specific use cases
• Build foundational knowledge of generative AI, including large language models (LLMs)
• Use empirical scaling laws to optimize the model’s objective function across dataset size, compute budget, and inference requirements
• Apply state-of-the art training, tuning, inference, tools, and deployment methods to maximize the performance of models within the specific constraints of your project
• Discuss the challenges and opportunities that generative AI creates for businesses after hearing stories from industry researchers and practitioners

Course content

Introduction to Generative AI Fundamentals

• Foundational knowledge needed about generative AI: what it is, how it’s applied, and explanations of some popular algorithms and architectures for text and image generation.
• Range of techniques for adapting foundation models, including prompt tuning, in-context learning, full fine-tuning, and parameter-efficient fine-tuning (PEFT).

Apply Lightweight Fine-Tuning to a Foundation Model

• Load and customize a Hugging Face foundation model using parameter-efficient fine-tuning. This technique allows you to harness the power of a pre-trained model for your custom task.

Generative AI versus Traditional AI

• Technical context and overview of differences between Gen AI and Traditional AI in the ML field
• This lesson explores foundation models in AI, how they differ from traditional models, how you can apply them to various tasks and evaluate their performance, and the ethical implication of their use.

Component parts of Model Selection/Model Evaluation/Model Deployment

• Different methods and platforms for deploying LLMs, how many users, latency expected

Prompt Engineering “Primer”

• Chat-Tuned vs Base-Model Prompting, Few Shot Prompting, Co-Star Framework

RAG versus Fine-Tuning/PEFT

Introduction to LLMs

• Types of LLMs, an intuitive understanding of their limitations and capabilities, inference and decoding hyperparameters, and strategies for effective prompt engineering.
• Construct a relevant, quality dataset for fine-tuning large language models and performing retrieval augmented generation.

Processing Raw Data with Gen AI/LLMs

• Pre-processing before inputs

Introduction to Image Generation

• Define image generation and understand its relevance in AI and machine learning.
• Image Generation and GANs
• Explore the landscape of Gen AI tools for Computer Vision and learn how they are evaluated. Learn what a generative adversarial network is and how it is utilized to generate images.

Computer Vision Fundamentals

• Learn how computers see images and perform key image processing techniques using classic image processing techniques such as image transformation, noise reduction, and more.
• Vision Transformers and the architecture that makes them work. Along the way we will explore Vision Transformers like DALL-E, DINO, and SAM.

Agent-Based Architecture

Vectorization & Top Vector Database Solutions

Building API / LangChain Pipelines Using LLMs

• Introduction to Building Generative Apps
• Design and implementation of Generative AI using Large Language Models in features, applications, and solutions.
• Building Generative AI Solutions with Vector Databases
• Retrieval methods, and advanced indexing.
• Developing Generative AI Solutions with LangChain
• LangChain, a framework for working with large language models (LLM) and powering the next generation of AI apps.

Common use cases

• Building domain-specific chatbots, building image generation models

ROI of GenAI Implementations

• Performance measurement, e.g., hours liberated, cost efficiencies using LLMs and automation

Hyperscale and key alliance GenAI platforms, tools, and technologies

• AWS Sagemaker, GCP VertexAI & Gemini, NVIDIA NeMo

Perspectives on the future of Artificial General Intelligence (AGI)

To see the full course content Download now