Back to the full dot-point answer
NSWSoftware EngineeringQuick questions
Module 3: Software Automation
Quick questions on Machine learning applications in industry explained: HSC Software Engineering Module 3
10short Q&A pairs drawn directly from our worked dot-point answer. For full context and worked exam questions, read the parent dot-point page.
What is image recognition?Show answer
Computer vision systems classify or detect objects in images. Applications:
What is natural language processing (NLP)?Show answer
Systems that understand or generate human language. Applications:
What is recommendation systems?Show answer
Predict items a user is likely to want. Applications:
What is predictive maintenance?Show answer
Predict when industrial equipment will fail. Applications:
What is a worked Python example?Show answer
A simple sentiment analysis pipeline using scikit-learn:
What is deployment realities?Show answer
Deploying ML is more than training a model:
What is forgetting the deployment layer?Show answer
Training a model is the easy bit. Serving it reliably, monitoring it and retraining it are the hard parts. Markers reward mentioning MLOps activities.
What is treating image recognition as a solved problem?Show answer
Domain shift (different cameras, lighting, populations) breaks deployed models. Continuous evaluation matters.
What is conflating "ML system" with "deep learning"?Show answer
Many industrial deployments still use logistic regression, gradient-boosted trees or random forests. Deep learning is one tool, not the only one.
What is ignoring cost asymmetry?Show answer
In fraud, missing a fraud costs more than declining a real customer; in cancer screening, missing a tumour costs more than a false alarm. Evaluation must reflect costs, not just accuracy. :::