AI Fundamentals

AI Fundamentals

The concepts behind modern AI. Machine learning basics, neural networks, supervised vs unsupervised learning, transformers, LLMs, prompt engineering, and where AI fits in software engineering today.

FundamentalsTopics 1–15

·What Is AI?
·Linear Algebra for AI
·Partial Derivatives & Gradients
·Python for AI
·NumPy: The Math Engine
·Pandas: Data Wrangling
·How Machines Learn
·Activation Functions
·Gradient Descent & Optimizers
·Feedforward Neural Networks
·Convolutional Neural Networks
·Recurrent Networks & LSTMs
·The Attention Mechanism
·The Transformer Architecture
·Vision Transformers (ViT)

Start Fundamentals →

IntermediateTopics 11–20

·Training Dynamics
·Optimisation Algorithms
·Regularisation in Practice
·Normalisation Layers
·Transfer Learning & Fine-tuning
·Embeddings & Vector Spaces
·Large Language Models
·Tokens & Tokenisation
·Prompt Engineering Basics
·Retrieval-Augmented Generation

Start Intermediate →

AdvancedTopics 21–30

·Fine-Tuning Models
·RLHF & Alignment
·Multimodal AI
·AI Agents & Tool Use
·Evaluating AI Systems
·Hallucinations & AI Safety
·Scaling Laws
·Vector Databases
·AI Infrastructure & GPUs
·The Context Window, Deep

Start Advanced →

AppliedTopics 31–40

·Choosing a Model
·AI APIs in Practice
·Building an AI-Powered App
·Cost & Latency Optimisation
·AI in Production
·Structured Outputs & Function Calling
·AI Ethics & Bias
·Multiagent Systems
·The State of AI
·Career in AI Engineering

Start Applied →