# The Full Applied GenAI Curriculum

## Python Crash Course I

·        Python fundamentals

·        Experience writing simple Python programs

 

## Python Crash Course II

·        Jupyter Notebooks and Google Colab

·        Python Libraries for Machine Learning

·        Hands-on with Large Language Models

 ·        Accessing popular foundation models via their APIs

·        Working with open-source models via Huggingface Transformers

·        Working with Stable Diffusion, LoRA

 

## Gen AI Background

·        Overview of Generative AI

·        Applications of Generative AI

·        Recent History of Generative AI

·        Methods for Evaluating Generative AI Models

·        Ethical Considerations in Generative AI

 

## Neural Networks Background

·        Architecture of feedforward neural networks

·        Activation functions

·        Training neural networks

·        Recurrent Neural Networks (RNNs)

·        Convolutional Neural Networks (CNNs)

 

## Deep Dive into LLMs

·        Probabilistic language models

·        The Transformer Architecture

·        Scaling Laws

 

## Building Applications with LLMs

·        Retrieval-augmented generation (RAG)

·        Agents

·        LangChain as a toolkit for LLM applications 

 

## Training LLMs

·        Pretraining LLMs

·        Fine-tuning LLMs and LoRA

·        Instruction Tuning

·        Learning from Preferences (RLHF and DPO)

 

## GenAI for Images

·        Diffusion Process (DDPM) and Stable Diffusion

·        Latent Diffusion

·        Fine-tuning diffusion models and LoRA (Low-Rank Adaptation of Large Language Models)

·        Visual Transformers and applications

## GenAI for Audio

·        Overview of Text-to-Speech Synthesis: Waveform Generation techniques

·        Creating New Music and Sounds with WaveNet and GANs

·        Voice Models and Architecture: Vocoders, Tacotron, etc.

·        Integrating Voice with LLMs

## Hands-On Project

·        Create LLM-based applications

 


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://metaverse-imagen.gitbook.io/ai-tools-research/about-ai-tools-research/ai-adoption-consultation-and-training-services/training-services/training-courses/the-full-applied-genai-curriculum.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.