Public

100 Days of Generative AI Fundamentals

Master generative AI concepts from foundational theory to practical applications. Progress through understanding AI basics, neural networks, transformers, and building your own generative models.

Level: beginnerCreated: 1/23/2026

This plan is public and visible in the Learning Plans Library.

Prerequisites

•Basic Python programming
•Understanding of statistics
•Familiarity with algebra

Learning Outcomes

✓Understand generative AI principles and architectures
✓Build and train basic generative models
✓Work with Large Language Models and image generation
✓Implement practical AI applications
✓Deploy generative AI solutions

Weekly Breakdown

Week Goals

• Understand AI and machine learning basics
• Learn about generative vs discriminative models

Day 1

AI Overview

Introduction to artificial intelligence, machine learning, and deep learning fundamentals.

Tasks

→Define AI, ML, DL concepts
→Explore real-world AI applications

Day 2

Generative Models Intro

Learn what generative models are and how they differ from discriminative models.

Tasks

→Compare generative vs discriminative
→Study use cases for each type

Day 3

Neural Networks Basics

Understand perceptrons, neurons, and basic neural network architecture.

Tasks

→Learn neuron mechanics
→Explore network layers and activation functions

Day 4

Forward Propagation

Study how data flows through neural networks.

Tasks

→Trace forward pass example
→Practice with simple networks

Day 5

Backpropagation Basics

Introduction to how neural networks learn through gradient descent.

Tasks

→Understand gradient calculation
→Study weight update process

Day 6

Loss Functions

Learn different loss functions and their applications in neural networks.

Tasks

→Explore MSE, Cross-entropy, and other losses
→Understand when to use each

Day 7

Optimization Techniques

Study optimizers like SGD, Adam, and RMSprop.

Tasks

→Compare optimization algorithms
→Implement basic gradient descent