AI & Machine Learning Course Build Real Models

The ML foundation every AI engineer must master before deep learning.

• Supervised learning workflow
• Regression and classification
• Decision trees and random forests
• Gradient boosting
• Model evaluation
• Cross-validation and tuning
• Feature engineering
• Unsupervised learning and clustering

Module outcome: You build and tune ensemble models on real data.

How neural networks work and how to build them from the ground up.

• Perceptrons and activation
• Forward and back propagation
• Loss functions and optimisers
• Building networks in TensorFlow
• Building networks in PyTorch
• Regularisation and dropout
• Training and debugging
• GPU and Colab

Module outcome: You train a neural network in both TensorFlow and PyTorch.

Teaching machines to see, from image classification to object detection.

• Convolutional neural networks
• Image classification
• Data augmentation
• Transfer learning
• Object detection basics
• Pre-trained models
• Image pipelines
• CV project workflow

Module outcome: You build an image classifier with transfer learning.

Working with text, from classic NLP to transformer models.

• Text preprocessing and tokenisation
• Word embeddings
• Text classification
• Sequence models (RNN, LSTM)
• Attention and transformers
• Using pre-trained models (Hugging Face)
• Sentiment and NER
• NLP pipelines

Module outcome: You build a text classifier using a transformer model.

The part most courses skip: getting models into production reliably.

• Saving and serving models
• Building an inference API (FastAPI)
• Docker for ML
• Model versioning
• Monitoring and drift
• Batch vs real-time inference
• Cost and latency
• Deploying to the cloud

Module outcome: You deploy a model as a containerised API.

A practical bridge into modern generative AI and how it is engineered.

• How LLMs work
• Prompting and prompt patterns
• Embeddings and vector search
• Retrieval-augmented generation
• Fine-tuning basics
• Using AI APIs
• Guardrails and evaluation
• When to build vs buy

Module outcome: You build a small RAG application over your own data.

A deployed AI system end to end plus interview and portfolio preparation.

• Capstone: design and build an AI system
• Data to trained model to API
• Presentation to a panel
• Portfolio and GitHub
• AI/ML interview prep
• ML system design basics
• Resume and LinkedIn review
• Placement pipeline onboarding

Module outcome: You ship a deployed AI capstone and interview-ready portfolio.