• Post category:StudyBullet-15
  • Reading time:7 mins read


Generative AI – English version

What you will learn

Generative AI definition, areas of applications, mappings like txt2txt, img2txt, txt2img and txt2voice

How ChatGPT works, and the underlying tech behind like GPT, Large-Scale Language Models (LLM) and Transformers

How Latent Diffusion, StableDiffusion and DALL-E systems work

Generative Adversarial Networks (GANs) and Variational Auto Encoder (VAE)

The good, bad and ugly faces of GenAI, and how to adapt to the new tech

Build ChatGPT clone using OpenAI API and Streamlit

Build NLP applications using OpenAI API like Summarization, Text Classification and fine tuning GPT models

Build NLP applications using Huggingface transformers library like Language Models, Summarization, Translation, QA systems and others

Build Midjourney clone application using OpenAI DALL-E and StableDiffusion on Huggingface

Description

Hello and Welcome to a new Journey in the vast area of Generative AI

Generative AI is changing our definition of the way of interacting with machines, mobiles and computers. It is changing our day-to-day life, where AI is an essential component.

This new way of interaction has many faces: the good, the bad and the ugly.


Get Instant Notification of New Courses on our Telegram channel.


In this course we will sail in the vast sea of Generative AI, where we will cover both the theoretical foundations of Generative models, in different modalities mappins: Txt2Txt, Img2Txt, Txt2Img, Img2Txt and Txt2Voice and Voice2Text. We will discuss the SoTA models in each area at the time of this course. This includes the SoTA technology of Transformers, Language models, Large LM or LLM like Generative Pre-trained Transformers (GPT), paving the way to ChatGPT for Text Generation, and GANs, VAE, Diffusion models like DALL-E and StabeDiffusion for Image Generation, and VALL-E foe Voice Generation.

In addition, we will cover the practical aspects, where we will build simple Language Models, Build a ChatGPT clone using OpenAI APIs where we will take a tour in OpenAI use cases with GPT3.5 and ChatGPT and DALL-E. In addition we will cover Huggingface transformers and StableDiffusion.

Hope you enjoy our journey!

English
language

Content

Introduction

Introduction
Course overview

What is Generative AI?

What is Generative AI?
Generative vs. Discriminative models
Why Generative models?
Encoder-Decoder design pattern
GenAI modalities mappings

Txt2Txt GenAI

Unimodal mappings: Txt2txt and Language models
Statistical Language Models (SLM)
Neural Language Models (NLM) – Char level
Neural Language Models (NLM) – Word level
SLM and NLM in Python and Keras
Seq2seq models
Seq2seq + Attention models
Transformers
Huggingface Transformer Pipeline
Large-Scale Language Models (LLM) – Transfer Learning in NLP
Pre-trained Transformers
BERT
GPT
ChatGPT
OpenAI API
GPT-3 Finetuning
GPT-3 Chatbot
ChatGPT Clone in Google Colab
ChatGPT Clone in Streamlit
ChatGPT Clone Excercise

Img2Img GenAI

Img2Img Encoder-Decoder
Auto Encoder (AE)
AE Visualization
Variational Auto Encoder (VAE)
Conditional VAE
Coding AE in Keras
Generative Adversarial Nets (GANs)
Generating images from GANs
Training GANs
Coding GAN training in Keras
DCGAN
Conditional GANs
AttributeGAN
How Good are GANs today?
Domain adaptation with pix2pix and CycleGAN

Multi-modal GenAI

Multimodal Txt2Img generation
Diffusion models
Latent Diffusion Models (LDM)
CLIP
StableDiffusion
Online tools for txt2img: DreamStudio and Midjourney
OpenAI API – DALL-E
Huggingface – StableDiffusion
Excercise – Midjourney clone
Img2Txt generation – Image Captioning
Txt2Voice generation – VALL-E

The good, the bad and the ugly

The Good
The Bad
The Ugly
What should we do?

Conclusion

Conclusion

Material

Material