⇽ Home

<aside> <img src="/icons/compose_purple.svg" alt="/icons/compose_purple.svg" width="40px" />

These are my notes after every session class taken with the LLM Claude AI to understand the foundations and basics of AI. I decided to follow this approach because allows me to interactively reasoning with the AI and set the conditions of learning like:

• Follow a curriculum by establishing connections between digital and biological neural networks (brain and digital neurons)
• Explanations for a nine-years old kid
• Build the learning process with the best education practices to reinforce my learning in the long-term </aside>

Study Notes

📍AI Learning Roadmap 🗺️

Foundations of Information Processing

<aside> <img src="/icons/condense_orange.svg" alt="/icons/condense_orange.svg" width="40px" />

Week 1: Binary and Basic Decision Making

• Binary number systems and patterns (completed December 28, 2024 )
• Simple threshold decisions (completed December 28, 2024 )
• Multiple input decisions and logic gates (completed January 1, 2025 ) </aside>

<aside> <img src="/icons/mathematics_orange.svg" alt="/icons/mathematics_orange.svg" width="40px" />

Week 2: From Logic to Neurons

• How neurons make decisions (completed January 1, 2025)
  • Universal Gates (NAND/NOR)
  • Layer and decision boundaries
• Neural Adjustments and learning (completed February 7, 2025)
  • Introduction to weights and biases
• Simple pattern recognition (completed February 7, 2025)
• Basic neural connections </aside>

<aside> <img src="/icons/light-bulb_orange.svg" alt="/icons/light-bulb_orange.svg" width="40px" />

Week 3: Pattern Recognition Basics

• How systems detect simple patterns
• Introduction to feature detection
• Basic statistical concepts (mean, variance)
• Pattern matching exercises </aside>

<aside> <img src="/icons/square-one-fourth_orange.svg" alt="/icons/square-one-fourth_orange.svg" width="40px" />

Week 4: Building Blocks of Learning

• How systems learn from examples

• Introduction to simple learning rules

• Error correction basics

• Practice with simple learning scenarios </aside>

• Transition template