Basic AI Course

Lesson 1 • AI's Impact Across Industries

Surveys how AI transforms healthcare, finance, manufacturing, and retail. Motivates learners by connecting theory to tangible professional outcomes.

Lesson 2 • Core AI Subfields Overview

Maps the major subfields—machine learning, NLP, computer vision, robotics—and their relationships. Prepares learners to categorise AI applications accurately.

Lesson 3 • Defining Artificial Intelligence

Establishes a precise, working definition of AI distinct from automation and software. Grounds the chapter by clarifying what AI can and cannot do.

Lesson 1 • Data Collection and Sourcing

Covers primary collection, open datasets, and synthetic data generation methods. Equips learners to source appropriate data for specific AI tasks.

Lesson 2 • Types of Data in AI

Distinguishes structured, unstructured, and semi-structured data and their AI use cases. Sets the stage for understanding which algorithms suit which data types.

Lesson 3 • Data Governance and Privacy

Introduces responsible data handling, consent, and privacy-preserving techniques. Ensures learners apply ethical standards when managing AI datasets.

Lesson 4 • Data Preprocessing Essentials

Teaches normalisation, encoding, and feature engineering as prerequisites to training. Directly enables learners to prepare datasets for the machine learning chapter.

Lesson 1 • Model Evaluation and Metrics

Teaches accuracy, precision, recall, F1, and AUC for assessing model quality. Enables learners to judge whether a model meets business requirements.

Lesson 2 • Reinforcement Learning Basics

Introduces agents, environments, rewards, and policies at a conceptual level. Prepares learners to recognise RL applications without requiring deep maths.

Lesson 3 • Unsupervised Learning Concepts

Covers clustering and dimensionality reduction for unlabelled data exploration. Expands learners' toolkit beyond labelled-data scenarios.

Lesson 4 • Supervised Learning Concepts

Explains regression and classification using labelled data with clear input-output mappings. Builds the primary algorithmic vocabulary used throughout the course.

Lesson 1 • Recurrent Neural Networks and Sequences

Introduces RNNs and LSTMs for sequential and time-series data processing. Bridges neural network theory to natural language and forecasting applications.

Lesson 2 • Training Neural Networks

Explains backpropagation, gradient descent, and learning rate as the training engine. Demystifies why neural networks improve with more data and iterations.

Lesson 3 • Anatomy of a Neural Network

Breaks down neurons, layers, weights, and activation functions as building blocks. Provides the structural vocabulary needed for all subsequent deep learning topics.

Lesson 4 • Convolutional Neural Networks

Covers CNN architecture for image recognition tasks including filters and pooling. Connects deep learning theory to computer vision applications introduced earlier.

Lesson 1 • Large Language Models Overview

Surveys pre-trained LLMs, fine-tuning, and prompt engineering for practical NLP tasks. Prepares learners to leverage LLMs without training from scratch.

Lesson 2 • Transformer Architecture Essentials

Explains attention mechanisms and the transformer model that powers modern NLP. Provides the conceptual foundation for understanding large language models.

Lesson 3 • Text Preprocessing Pipeline

Covers tokenisation, stemming, lemmatisation, and stopword removal as NLP prerequisites. Prepares raw text for downstream modelling tasks.

Lesson 4 • Core NLP Tasks

Demonstrates sentiment analysis, named entity recognition, and text classification. Gives learners hands-on exposure to the most common NLP business applications.

Lesson 1 • Image Data Fundamentals

Covers pixel representation, colour spaces, and image formats as vision prerequisites. Ensures learners understand the raw material before applying algorithms.

Lesson 2 • Transfer Learning for Vision

Demonstrates using pre-trained vision models and fine-tuning for custom datasets. Enables learners to build high-performing vision systems with limited data.

Lesson 3 • Image Preprocessing and Augmentation

Teaches resizing, normalisation, and augmentation strategies to improve model robustness. Directly applies data preparation skills to the vision domain.

Lesson 4 • Object Detection and Localisation

Introduces bounding boxes, anchor-based detectors, and evaluation with IoU metrics. Extends image classification to locating multiple objects in a scene.

Lesson 1 • Experiment Tracking and Versioning

Introduces tools and practices for logging experiments, datasets, and model versions. Ensures reproducibility and collaboration across AI development teams.

Lesson 2 • Model Packaging and Serving

Covers serialisation formats, REST APIs, and containerisation for model deployment. Bridges the gap between a trained model and a production-ready service.

Lesson 3 • Monitoring Models in Production

Teaches data drift detection, performance degradation alerts, and retraining triggers. Ensures deployed models remain accurate and reliable over time.

Lesson 4 • AI Project Lifecycle

Maps the stages from problem framing through deployment and maintenance. Gives learners a structured workflow to manage any AI project professionally.

Lesson 1 • Societal and Workforce Impacts

Analyses AI's effects on employment, privacy, and power concentration. Develops critical thinking about long-term consequences of AI deployment decisions.

Lesson 2 • Explainability and Transparency

Covers LIME, SHAP, and model cards as tools for explaining AI decisions. Enables learners to make black-box models interpretable to stakeholders.

Lesson 3 • Responsible AI Frameworks

Surveys industry and regulatory responsible AI principles and governance structures. Prepares learners to align AI projects with organisational and societal standards.

Lesson 4 • Sources of Bias in AI

Identifies how historical, measurement, and aggregation biases enter AI systems. Grounds ethical analysis in concrete technical causes rather than abstract concerns.