AI Foundations

Master the logic behind neural networks and machine learning from a developer's perspective. You will build a solid mental model of how algorithms transform raw data into intelligent predictions. * **Core terminology** including machine learning and neural networks * **Algorithm mechanics** explaining how models process data * **Technical architecture** of modern generative AI systems * **Practical logic** behind training and deploying models

8 sections ยท 36 lessons

Course outline

Language Models Basics

  1. Inside ChatGPT
  2. How Prompts Work
  3. Probability & Randomness
  4. Temperature
  5. Language Models Basics

How Models Learn

  1. Training Data Scale
  2. Generalization
  3. Parameters
  4. Tuning the Model

Training in Practice

  1. The Training Process
  2. Developing Understanding
  3. Scale of Computation
  4. Hardware Reality

Making AI Helpful

  1. Pre-training Basics
  2. Supervised Fine-Tuning
  3. Reinforcement Learning
  4. Complete Training Pipeline
  5. GPU Technology
  6. The Parallelization Problem

Transformer Innovation

  1. Introduction to Transformers
  2. Words to Numbers
  3. Understanding Embeddings
  4. Introduction to Attention
  5. How Attention Works

Connecting the Pieces

  1. Feed-Forward Networks
  2. Multi-Layer Basics
  3. From Vectors to Predictions
  4. Complete Pipeline

AI Strengths & Limitations

  1. What LLMs Excel At
  2. Next to Master
  3. Core LLM Limitations
  4. Structural Constraints

Practical AI Use

  1. Prompt Engineering Fundamentals
  2. Advanced Prompting Techniques
  3. AI Literacy: Engaging & Creating
  4. AI Literacy: Managing & Designing
  5. Your AI-Augmented Future

Start learning with Wondering