Home Memorise Flashcards Notes Master answers Past questions Multiple choice Mock exam Practice & marker

Software Engineering › Flashcards › Software Automation (Year 12)

Software Automation (Year 12)

36 flashcards (Year 12). Study these as flip cards Random

Machine learning and automation

Machine learning (ML) Term

A branch of AI where a program learns patterns from data to make predictions or decisions without being explicitly programmed with fixed rules.

Example: 'A spam filter learns from labelled emails.'

Where you would use it in the test

Multiple choice: Multiple choice: pick the option that matches the definition or example.
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.
Fill in the blanks: Fill in the blanks or dropdown: choose this term to complete a statement or table.

Memorise: AI v ML; ML supporting automation (DevOps, RPA, BPA)

Artificial intelligence (AI) Term

The broad field of making computers perform tasks that normally need human intelligence (reasoning, understanding language, recognising images). ML is one way of achieving AI.

Example: 'All ML is AI but not all AI is ML.'

Where you would use it in the test

Short answer: Distinguish AI from ML or neural networks (2025 Q25)
Multiple choice: Multiple choice: pick the option that matches the definition or example.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.

Memorise: AI v ML; ML supporting automation (DevOps, RPA, BPA)

Distinguishing AI and ML Term

AI is the goal of intelligent behaviour; ML is the method of learning from data. A neural network is one ML model.

Example: 2025 Q25 marker note: state a clear difference between neural networks and AI rather than describing each separately.

Where you would use it in the test

Short answer: Distinguish
Multiple choice: Multiple choice: pick the option that matches the definition or example.

Memorise: AI v ML; ML supporting automation (DevOps, RPA, BPA)

DevOps Term

A way of working that joins development (Dev) and operations (Ops) with automation, continuous integration and delivery, monitoring and collaboration so software is released faster and more reliably.

Example: 'Automate testing and deployment in a pipeline.'

Where you would use it in the test

Multi-select: 2025 Q11: identify ALL the key principles of DevOps
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Multiple choice: Multiple choice: pick the option that matches the definition or example.

Memorise: AI v ML; ML supporting automation (DevOps, RPA, BPA)

Robotic process automation (RPA) Term

Software 'bots' that copy the actions a person does on a computer (clicking, typing, copying data) to automate repetitive, rule-based tasks.

Example: 'A bot copies invoice data into the accounting system.'

Where you would use it in the test

Multiple choice: Multiple choice: pick the option that matches the definition or example.
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.

Memorise: AI v ML; ML supporting automation (DevOps, RPA, BPA)

Business process automation (BPA) Term

Using software to automate a whole business process or workflow (for example approvals, payroll or order processing) to cut cost and errors.

Example: 'Automatic approval of leave requests.'

Where you would use it in the test

Multiple choice: Multiple choice: pick the option that matches the definition or example.
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.

Memorise: AI v ML; ML supporting automation (DevOps, RPA, BPA)

Training models

Supervised learning Term

Training on labelled data (inputs paired with correct outputs) so the model can predict the label for new data.

Example: 'Photos labelled cat or dog train an image classifier.'

Where you would use it in the test

Multiple choice: 2025 Q3
Matching or table: Matching or table question: match it to its description, example or category.
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Fill in the blanks: Fill in the blanks or dropdown: choose this term to complete a statement or table.

Related past questions: 2025 HSC Q3 (1 mark): Machine learning training

Memorise: Models of training ML

Unsupervised learning Term

Training on unlabelled data so the model finds patterns or groups (clusters) by itself.

Example: 'Group customers by buying habits.'

Where you would use it in the test

Multiple choice: Multiple choice: pick the option that matches the definition or example.
Matching or table: Matching or table question: match it to its description, example or category.
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Fill in the blanks: Fill in the blanks or dropdown: choose this term to complete a statement or table.

Related past questions: 2025 HSC Q3 (1 mark): Machine learning training

Memorise: Models of training ML

Semi-supervised learning Term

Training with a small amount of labelled data and a large amount of unlabelled data.

Example: 'Label a few images, let the model help label the rest.'

Where you would use it in the test

Multiple choice: Multiple choice: pick the option that matches the definition or example.
Matching or table: Matching or table question: match it to its description, example or category.
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Fill in the blanks: Fill in the blanks or dropdown: choose this term to complete a statement or table.

Related past questions: 2025 HSC Q3 (1 mark): Machine learning training

Memorise: Models of training ML

Reinforcement learning Term

The model learns by trial and error, receiving rewards or penalties for its actions in an environment, to maximise reward.

Example: 'A robot learns to walk by being rewarded.'

Where you would use it in the test

Multiple choice: Multiple choice: pick the option that matches the definition or example.
Matching or table: Matching or table question: match it to its description, example or category.
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Fill in the blanks: Fill in the blanks or dropdown: choose this term to complete a statement or table.

Related past questions: 2025 HSC Q3 (1 mark): Machine learning training

Memorise: Models of training ML

Training data and test data Term

Training data is used to teach the model; separate test data checks how well it works on data it has not seen.

Example: 'Hold back 20% of the data for testing.'

Where you would use it in the test

Multiple choice: Multiple choice: pick the option that matches the definition or example.
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Fill in the blanks: Fill in the blanks or dropdown: choose this term to complete a statement or table.

Memorise: Models of training ML

Check this one: Standard ML practice; check the exact wording against your class notes.

Applications of ML

Data analysis and forecasting Term

ML finds trends in past data to predict future values (sales, weather, demand).

Example: 'Forecast next month's electricity demand.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.
Multiple choice: Multiple choice: pick the option that matches the definition or example.

Memorise: Applications of key ML algorithms

Virtual personal assistant Term

Software (Siri, Alexa) that uses ML to understand speech or text and do tasks such as set reminders, improving as it learns.

Example: 'A voice assistant learns your accent.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.
Multiple choice: Multiple choice: pick the option that matches the definition or example.

Memorise: Applications of key ML algorithms

Image recognition Term

ML identifying objects, faces or text in images, usually with neural networks trained on many labelled images.

Example: 'Detect faces in photos.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.
Multiple choice: Multiple choice: pick the option that matches the definition or example.

Memorise: Applications of key ML algorithms

Designing and analysing ML models

Decision tree Diagram

A flowchart-like model where each internal node tests a condition, branches are outcomes and leaves are decisions or predictions.

Example: 'Is it raining? yes: take umbrella; no: next test.'

Where you would use it in the test

Drawing: Draw or complete a decision tree (sample Q20, fam Q7)
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Multiple choice: Multiple choice: pick the option that matches the definition or example.

Memorise: Decision trees

Neural network Term

A model made of connected layers of nodes (neurons): an input layer, one or more hidden layers and an output layer; connection weights are adjusted during training.

Example: 2025 Q25: a neural network is one technique within AI.

Where you would use it in the test

Short answer: Distinguish a neural network from AI (2025 Q25)
Multiple choice: Multiple choice: pick the option that matches the definition or example.
Python: Python question: write or complete it in the online Python tool.

Memorise: Decision trees

Linear regression Term

Fits a straight line through data to predict a numeric value from one or more inputs.

Example: 'Predict house price from floor area.'

Where you would use it in the test

Short answer: Compare linear regression and KNN (sample Q23b)
Multiple choice: Multiple choice: pick the option that matches the definition or example.
Python: Python question: write or complete it in the online Python tool.

Memorise: Decision trees

Polynomial regression Term

Fits a curve (a polynomial) to data where the relationship is not a straight line, to predict a numeric value.

Example: 'Predict plant growth that speeds up then slows down.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Multiple choice: Multiple choice: pick the option that matches the definition or example.
Python: Python question: write or complete it in the online Python tool.

Memorise: Decision trees

Logistic regression Term

Predicts the probability of a category (yes or no) and so is used for classification, not for predicting a number.

Example: 'Predict whether an email is spam.'

Where you would use it in the test

Multiple choice: 2025 Q12: true or false statements
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Python: Python question: write or complete it in the online Python tool.

Related past questions: 2025 HSC Q12 (2 marks): Logistic regression

Memorise: Decision trees

K-nearest neighbour (KNN) Term

Classifies a new item by looking at the K closest items in the training data and choosing the most common class among them.

Example: 'With K = 3, the three nearest points vote.'

Where you would use it in the test

Short answer: Compare with linear regression (sample Q23b)
Multiple choice: Multiple choice: pick the option that matches the definition or example.

Memorise: Decision trees

OOP for ML programming Code pattern

ML models are written as classes: attributes hold data and weights, methods train, predict and evaluate.

Example: 'model = LinearRegression(); model.fit(x, y); model.predict([[5]])'

Where you would use it in the test

Python: Python question: write or complete it in the online Python tool.
Code reading: Code or algorithm reading: interpret a fragment and state its output or purpose.
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.

Memorise: Decision trees

Neural network code (predict) Code pattern

Create the model object, train (fit) on training data, then call predict on new data to make predictions.

Example: 'net.fit(X, y); net.predict(new)'

Where you would use it in the test

Python: Python question: write or complete it in the online Python tool.
Code reading: Code or algorithm reading: interpret a fragment and state its output or purpose.

Memorise: Decision trees

Significance and impact

Impact of automation Term

Effects on safety of workers, people with disability, the nature and skills required for employment, production efficiency, waste and the environment, and the economy and distribution of wealth.

Example: 2025 Q24 marker note: use the stimulus and give positives and negatives.

Where you would use it in the test

Short answer: Discuss the impact of automation on workers (2025 Q24)
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.

Memorise: Impact of automation on individuals, society and the environment

Safety of workers Term

Robots take over dangerous tasks (positive) but can cause injury or stress if poorly designed (negative).

Example: 'Robots handle toxic chemicals.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.

Memorise: Impact of automation on individuals, society and the environment

People with disability Term

Automation can improve access (voice control, assistive devices) but can also exclude people if not designed accessibly.

Example: 'Voice assistants help people with limited mobility.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.

Memorise: Impact of automation on individuals, society and the environment

Nature and skills of employment Term

Jobs change: routine roles shrink; demand grows for design, maintenance and data skills; retraining is needed.

Example: 'Factory workers retrain as robot technicians.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.

Memorise: Impact of automation on individuals, society and the environment

Production efficiency, waste and the environment Term

Automation can increase output and reduce waste and errors but uses energy and creates electronic waste.

Example: 'Precision machines reduce material waste.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.

Memorise: Impact of automation on individuals, society and the environment

Economy and distribution of wealth Term

Automation can lift productivity and profit but may concentrate wealth with owners and cut incomes of displaced workers.

Example: 'Savings go to shareholders while jobs are lost.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.

Memorise: Impact of automation on individuals, society and the environment

Patterns in human behaviour Term

How people's behaviour affects ML and AI design: psychological responses, patterns related to acute stress response (fight, flight, freeze), cultural protocols and belief systems.

Example: 'An alert system must not overload a person under stress.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.
Multiple choice: Multiple choice: pick the option that matches the definition or example.

Memorise: Impact of automation on individuals, society and the environment

Dataset source bias Term

Unfair results because the training data is unrepresentative or reflects past prejudice.

Example: 'A face detector trained mostly on one group fails on others.'

Where you would use it in the test

Short answer: Explain bias in AI (2025 Q27, sample Q23a)
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.
Multiple choice: Multiple choice: pick the option that matches the definition or example.

Memorise: Impact of automation on individuals, society and the environment

Human bias Term

Developers' own assumptions or prejudices influence design, data selection or labelling and so the outcomes.

Example: 'Labellers' opinions shape the labels.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Extended response: Extended response (5 to 8 marks): use it as a supporting point linked to the stimulus.
Multiple choice: Multiple choice: pick the option that matches the definition or example.

Memorise: Impact of automation on individuals, society and the environment

MLOps

MLOps Term

The automated process of designing, training and deploying ML models, borrowing the principles of DevOps. The three stages are Design, Model development and Operations.

Example: 'Design, then model development, then operations.'

Where you would use it in the test

Multiple choice: Multiple choice: pick the option that matches the definition or example.
Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Drag into order: Order the MLOps stages

Related past questions: 2025 HSC Q11 (1 mark): DevOps

Memorise: AI v ML; ML supporting automation (DevOps, RPA, BPA)

MLOps design stage Term

Define the business problem, refactor it into a machine learning problem, define success metrics and research the available data.

Example: 'Success metric: 95% accuracy.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Multiple choice: Multiple choice: pick the option that matches the definition or example.
Drag into order: Drag into order: know where it sits in the sequence.

Memorise: AI v ML; ML supporting automation (DevOps, RPA, BPA)

MLOps model development stage Term

Data wrangling, feature engineering, model training, and model testing and validation.

Example: 'Clean the data, then train the model.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Multiple choice: Multiple choice: pick the option that matches the definition or example.
Drag into order: Drag into order: know where it sits in the sequence.

Memorise: AI v ML; ML supporting automation (DevOps, RPA, BPA)

MLOps operations stage Term

Model deployment, supporting operations and use, and monitoring model performance.

Example: 'Monitor the model for drift.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Multiple choice: Multiple choice: pick the option that matches the definition or example.
Drag into order: Drag into order: know where it sits in the sequence.

Memorise: AI v ML; ML supporting automation (DevOps, RPA, BPA)

Neural network training and execution cycle Term

In the training cycle, weightings and threshold values for each node are set by exposing the network to inputs with known responses. In the execution cycle, those learned values are used to produce the output. Stronger weightings mean higher priority.

Example: 'Training sets the weights; execution uses them.'

Where you would use it in the test

Short answer: Short answer (2 to 4 marks): define, outline or explain it and tie it to the scenario.
Multiple choice: Multiple choice: pick the option that matches the definition or example.

Memorise: AI v ML; ML supporting automation (DevOps, RPA, BPA)

← Programming for the Web (Year 12)The Software Engineering Project (Year 12) →