AI & Machine Learning
Master artificial intelligence and ML — 50 lessons from your first model to advanced LLMs, computer vision, and production deployment.
Sign in to track your progress through this course
👋 New to AI? The best time to start is now.
You'll need basic Python — if you have that, you're ready. Start with Lesson 1 and build your first ML model.
Beginner Track
✦ Start Here ~2–3 hoursUnderstand what AI and ML are, set up Python, and train your first real machine learning models.
Introduction to AI & ML
What AI and machine learning are, and what you'll be able to build
Python for Machine Learning
NumPy, Pandas, and Matplotlib — the essential Python tools for ML
Data Preprocessing
Clean, transform, and prepare raw data before training any model
Linear Regression
Predict continuous values — your first machine learning model
Classification Basics
Categorise data into classes using logistic regression and k-NN
Intermediate Track
~3–4 hoursBuild decision trees, neural networks, and apply ML to real language and image tasks.
Decision Trees & Random Forests
Build interpretable tree models and ensemble them into random forests
Neural Networks Introduction
Understand neurons, layers, weights, and how neural networks learn
Deep Learning Fundamentals
Train deep neural networks with backpropagation and activation functions
Natural Language Processing
Process and understand text — tokenisation, embeddings, and sentiment analysis
Computer Vision Basics
Teach computers to understand images with CNNs and image classification
Expert Track
~3–4 hoursMaster advanced neural networks, transformers, reinforcement learning, and production deployment.
Advanced Neural Networks
Regularisation, batch normalisation, dropout, and advanced architectures
Transformers & LLMs
How attention mechanisms power GPT, BERT, and large language models
Reinforcement Learning
Train agents to make decisions with rewards, policies, and Q-learning
Model Deployment
Serve ML models in production with FastAPI, Docker, and cloud platforms
Advanced Track
~12–16 hoursCutting-edge AI engineering — LLMs, RAG, diffusion models, MLOps, distributed training, and ethical AI.
Advanced Optimization Techniques (AdamW, LookAhead, Cyclical LR)
AdamW, Lion, LR warmup, cosine annealing, and LR range tests
Data Augmentation Strategies for Images, Text & Audio
Expand small datasets with rotation, flipping, mixup, and text augmentation
Transfer Learning & Fine-Tuning Pretrained Models
Adapt pretrained models (ResNet, BERT) to new tasks with fine-tuning
Attention Mechanisms & Self-Attention Explained
Scaled dot-product attention, multi-head attention, and positional encoding
Transformer Architecture Deep Dive (Q/K/V, Multi-Head Attention)
Build a transformer from scratch — encoder, decoder, and positional embeddings
Building Custom CNN Architectures From Scratch
Design CNNs with conv layers, pooling, skip connections, and bottlenecks
Residual Networks (ResNet), DenseNets & Modern CNN Design
Understand skip connections, dense blocks, and modern CNN innovations
Training Stability Techniques: Normalization, Initialization, Gradient Clipping
Batch norm, layer norm, Xavier/He init, and gradient clipping for stable training
Generative Models: Autoencoders, VAEs & GANs
Build models that generate new data — autoencoders, VAEs, and GANs
Diffusion Models Explained (Stable Diffusion, DDPM)
How denoising diffusion models generate images from noise
Large Language Models Architecture (GPT, LLaMA, Mistral)
Decoder-only transformers, tokenisation, and the architecture of modern LLMs
Tokenization Strategies (BPE, WordPiece, SentencePiece)
How BPE, WordPiece, and SentencePiece convert text to tokens for LLMs
Fine-Tuning LLMs: LoRA, QLoRA & PEFT Techniques
Fine-tune LLMs efficiently on custom data with LoRA and QLoRA
Reinforcement Learning Basics (MDP, Policies, Rewards)
Markov Decision Processes, value functions, policies, and the Bellman equation
Q-Learning & Deep Q-Networks (DQN)
Implement Q-learning and DQN with experience replay and target networks
Policy Gradient Methods (REINFORCE, PPO, A2C)
Train agents directly on policy gradients with PPO and actor-critic methods
Computer Vision Pipelines with OpenCV & PyTorch/TensorFlow
Build end-to-end vision pipelines for classification, detection, and segmentation
Object Detection: YOLO, SSD & Faster R-CNN Models
Detect and localise objects in images with YOLO and two-stage detectors
Semantic Segmentation (U-Net, DeepLab, Mask R-CNN)
Label every pixel in an image with U-Net and DeepLab architectures
Speech Recognition & Audio ML Models
Build speech-to-text systems with Whisper, mel spectrograms, and CTC
Advanced NLP: Transformers, BERT, T5, LLaMA, Mistral
Fine-tune BERT for classification, T5 for generation, and LLaMA for chat
Building Retrieval-Augmented Generation (RAG) Systems
Combine LLMs with vector search to build knowledge-grounded chatbots
Vector Databases & Embeddings (FAISS, Pinecone, ChromaDB)
Store and search embeddings at scale with FAISS, Pinecone, and Chroma
Evaluating AI Models: F1, ROC, Perplexity, BLEU, WER
Choose and calculate the right metrics for classification, NLP, and generation tasks
Model Compression: Quantization, Pruning, Distillation
Make models smaller and faster with int8 quantisation, pruning, and distillation
Optimizing Models for CPU/GPU/TPU Deployment
Optimise inference for different hardware targets with ONNX, TensorRT, and XLA
Distributed Training with Data Parallelism & Model Parallelism
Train large models across multiple GPUs with DDP, FSDP, and pipeline parallelism
Serving ML Models: TorchServe, FastAPI, TensorFlow Serving
Deploy and serve ML models reliably with TorchServe, FastAPI, and TF Serving
Monitoring Models in Production (Drift, Outliers, Bias)
Detect data drift, outliers, and model degradation in production systems
MLOps Fundamentals: Pipelines, CI/CD, Versioning
Automate ML pipelines with MLflow, DVC, and CI/CD for model releases
Building Recommender Systems (Content, Collaborative, Hybrid)
Build content-based, collaborative filtering, and hybrid recommendation engines
Graph Neural Networks (GNNs) for Social & Knowledge Graphs
Apply GNNs to social networks, knowledge graphs, and molecular data
AutoML & Neural Architecture Search (NAS)
Automate model selection and architecture design with AutoML and NAS
Ethical AI, Bias Mitigation & Safety Principles in ML
Identify, measure, and reduce bias — build fair and responsible AI systems
Final AI Project — Build & Deploy a Full End-to-End ML System
Design, train, evaluate, and deploy a complete ML system from scratch