Generative AI using Python

Description

This course introduces the concepts and practical implementation of generative AI models using Python. Participants gain hands-on experience building and deploying models that create text, images, or other media, leveraging state-of-the-art libraries.

Indicative Duration: 36 training hours
*Duration is adjusted based on the final scope and the target audience.

Scope

1. Introduction
  • Machine Learning: Motivation, Terminology, Basic Concepts
  • Python basics, control flow, data structures, functions, classes and files
  • Numpy library: arrays and operations
  • Pandas library: data manipulation, handling missing values
  • Data Visualization: Use of matplotlib/seaborn libraries
2. Discriminative ML
  • Exploratory Data Analysis: Understand your data
  • Scikit-learn
  • Preprocessing (missing values, scalling, encoding)
  • Classification (Decision Trees, Logistic Regression, KNN)
  • Model Evaluation, Confusion Matrix and Metrics
  • Cross-Validation
  • Regression (Linear Regression)
  • Model Evaluation, Metrics
  • ML common issues (bias-variance tradeoff, regularization, class imbalance, over/under sampling, hyperparameter optimization)
  • Introduction to unsuvervised learning: Clustering, k-means, evaluating a clustering solution
3. Generative AI
  • Introduction to Generative AI
  • Setting up the Development Environment
  • Introduction to Tensorflow (keras) and PyTorch
  • Building small toy networks to understand the structure, process and workflow
  • Generative Adversarial Networks (GANs)
  • Understanding the architecture, training process and applications
  • Hands-on Example
  • – Implementing a simple GAN (using TensorFlow or PyTorch)
  • Introduction to autoencoders and their role in generative models
  • Variational Autoencoders and their concepts
  • Hands-on Example:
  • – Building a Variational Autoencoder (using TensorFlow or PyTorch)
  • Transformers for generation – The power behind ChatGPT
  • Model Architecture and Layers
  • Hands-on example:
  • – Implement a simple transformer for text generation (using TensorFlow or PyTorch)

Learning Objectives

Upon completion of the course participants will be able to:

  1. Understand the fundamental architectures behind generative AI, including GANs, VAEs, and transformers.
  2. Use Python libraries such as TensorFlow, PyTorch, and Hugging Face Transformers to build generative models.
  3. Train and fine-tune generative models for tasks like text generation, image synthesis, and audio production.
  4. Evaluate model outputs and optimize for quality and diversity.
  5. Integrate generative AI models into applications and workflows effectively.

Target Audience

  • Roles: Aspiring AI Engineers, Data Scientists, ML Developers, and Technical Researchers
  • Seniority Level: Intermediate to advanced professionals or graduate-level learners seeking hands-on expertise in generative AI

Prerequisite Knowledge

  • Working knowledge of Python programming
  • Basic understanding of machine learning principles and data structures
  • Prior exposure to ML frameworks (TensorFlow or PyTorch) is beneficial but not required

Delivery Method

Sessions can be delivered via the following formats:

  • Live Online – Interactive virtual sessions via video conferencing
  • On-Site – At your organization’s premises
  • In-Person – At Code.Hub’s training center
  • Hybrid – A combination of online and in-person sessions

 

The training methodology combines presentations, live demonstrations, hands-on exercises and interactive discussions to ensure participants actively practice AI in realistic work scenarios.

Tags:

Date

On Demand

Organizer

Code.Hub
Email
[email protected]