Module 3: Software Automation

6 dot points across 2 inquiry questions, in syllabus order. Each dot point has a focused answer, with exam-style questions and worked answers where available.

Inquiry Question 1: How do machine learning systems work?

Compare supervised, unsupervised and reinforcement learning, and identify a typical application of each

Learning paradigms. Supervised classification and regression, unsupervised clustering, reinforcement learning, applications of each, worked examples, and the traps markers look for.

10 min read →

Distinguish machine learning from classical programming, and define the roles of model, features, training data and predictions

What machine learning is. Classical programming vs ML, the role of training data, features, model and predictions, the worked example, and the traps markers look for.

9 min read →

Describe the basic structure of a neural network, including neurons, layers, weights, activation functions and training by backpropagation

Neural networks: neurons, layers, weights, activation functions, a network figure, forward pass and backpropagation, worked numeric examples and graded practice.

10 min read →

Inquiry Question 2: How are machine learning systems used to develop solutions?

Identify the ethical implications of automation and artificial intelligence, including accountability, transparency, employment effects and the use of personal data

AI ethics. Accountability, transparency, employment, personal data, real cases (COMPAS, Amazon hiring, Robodebt), the worked example, and the traps markers look for.

9 min read →

Describe applications of machine learning in industry, including image recognition, natural language processing, recommendation systems and predictive maintenance

ML applications: image recognition, NLP, recommendation systems, predictive maintenance, an MLOps lifecycle figure, worked examples, common traps, and graded practice.

9 min read →

Explain how the quality and representativeness of training data affect a model, including the risks of bias and overfitting

Training data. Sample bias, label bias, the train/test split, overfitting and underfitting, worked examples, and the traps markers look for.

10 min read →