top of page

Foundations first

​

TABLE OF CONTENT

PART I: The Big Picture

  1. What Is Artificial Intelligence?

    • Definition

    • Narrow vs. General vs. Super AI

  2. The Branches of AI​

    • Machine Learning

    • Robotics

    • Computer Vision

    • Natural Language Processing (NLP)

  3. A Brief History of AI

    • The Dartmouth Conference and early hopes

    • The AI winters

    • The deep learning revival

    • Transformers and the LLM era
       

PART II: Foundations of Machine Learning

  1. What Is Machine Learning?

    • Types: Supervised, Unsupervised, Reinforcement

    • Algorithms: Decision Trees, SVMs, k-NN, etc.

    • Key concepts: training, overfitting, bias-variance tradeoff

  2. From Data to Decisions

    • Data collection and preprocessing

    • Feature engineering

    • Model evaluation and tuning
       

PART III: Neural Networks & Deep Learning

  1. What Are Neural Networks?

    • Structure: neurons, layers, activations

    • Training: backpropagation, gradient descent

  2. Deep Learning Explained

    • Convolutional Neural Networks (CNNs)

    • Recurrent Neural Networks (RNNs)

    • Attention Mechanisms

    • Generative Adversarial Networks (GANs)
       

PART IV: Transformers and Language Models

  1. The Transformer Revolution

    • Why RNNs struggled with language

    • Self-attention, multi-head attention, positional encoding

    • Encoder vs. decoder vs. encoder-decoder

  2. Introduction to LLMs

    • What they are and how they work

    • Pre-training and fine-tuning

    • Why scale matters

  3. Notable LLMs Through the Years

    • GPT family, BERT, PaLM, Gemini, Claude, LLaMA

    • Open-source vs. proprietary models

    • Model architectures and breakthroughs
       

PART V: Using, Tuning, and Talking to LLMs

  1. Prompting 101

    • Prompts, zero-shot, few-shot

    • Chain-of-thought, ReAct, Role prompting

  2. Fine-Tuning and Alignment

    • Supervised fine-tuning

    • RLHF, RLAIF, DPO

    • Parameter-efficient methods (LoRA, QLoRA)

  3. Inference, Sampling, and Response Control

    • Sampling methods: Top-K, Top-P, temperature

    • Output control and decoding strategies

bottom of page