Generative AI for Beginners

• An understanding of basic programming concepts in Python
• Experience with basic mathematical concepts, especially probability and linear algebra

Audience

• Developers

Generative AI is a subset of artificial intelligence focused on creating new content, whether it be text, images, or other data types, that is similar to but not identical to the content it has learned from.

This instructor-led, live training (online or onsite) is aimed at beginner-level developers who wish to gain foundational knowledge and practical experience in Generative AI.

By the end of this training, participants will be able to:

• Understand the principles behind generative models and their applications.
• Implement basic generative models using TensorFlow or PyTorch.
• Generate new content using Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs).
• Explore the ethical implications of generative AI.
• Apply generative AI concepts to real-world scenarios.

Format of the Course

• Interactive lecture and discussion.
• Lots of exercises and practice.
• Hands-on implementation in a live-lab environment.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

Introduction to Generative AI

• What is Generative AI?
• History and evolution of Generative AI
• Key concepts and terminology
• Overview of applications and potential of Generative AI

Fundamentals of Machine Learning

• Introduction to machine learning
• Types of machine learning: Supervised, Unsupervised, and Reinforcement Learning
• Basic algorithms and models
• Data preprocessing and feature engineering

Deep Learning Basics

• Neural networks and deep learning
• Activation functions, loss functions, and optimizers
• Overfitting, underfitting, and regularization techniques
• Introduction to TensorFlow and PyTorch

Generative Models Overview

• Types of generative models
• Differences between discriminative and generative models
• Use cases for generative models

Variational Autoencoders (VAEs)

• Understanding autoencoders
• The architecture of VAEs
• Latent space and its significance
• Hands-on project: Building a simple VAE

Generative Adversarial Networks (GANs)

• Introduction to GANs
• The architecture of GANs: Generator and Discriminator
• Training GANs and challenges
• Hands-on project: Creating a basic GAN

Advanced Generative Models

• Introduction to Transformer models
• Overview of GPT (Generative Pretrained Transformer) models
• Applications of GPT in text generation
• Hands-on project: Text generation with a pre-trained GPT model

Ethics and Implications

• Ethical considerations in Generative AI
• Bias and fairness in AI models
• Future implications and responsible AI

Industry Applications of Generative AI

• Generative AI in art and creativity
• Applications in business and marketing
• Generative AI in science and research

Capstone Project

• Ideation and proposal of a generative AI project
• Dataset collection and preprocessing
• Model selection and training
• Evaluation and presentation of results

Summary and Next Steps