International Baccalaureate IB Computer Science

Describe the types of machine learning and their applications in the real world.
- The different approaches to machine learning algorithms and their unique characteristics
- Deep learning (DL), reinforcement learning (RL), supervised learning, transfer learning (TL), unsupervised learning (UL)
- Real-world applications of machine learning may include market basket analysis, medical imaging diagnostics, natural language processing, object detection and classification, robotics navigation, sentiment analysis.

Describe the hardware requirements for various scenarios where machine learning is deployed.
- The hardware configurations for different machine learning scenarios, considering factors such as processing, storage and scalability
- Hardware configurations for machine learning ranging from standard laptops to advanced infrastructure
- Advanced infrastructure must include application-specific integrated circuits (ASICs), edge devices, field-programmable gate arrays (FPGAs), GPUs, tensor processing units (TPUs), cloud-based platforms, high-performance computing (HPC) centres.

- Feature selection to identify and retain the most informative attributes of the data set
- Feature selection strategies: filter methods, wrapper methods, embedded methods

Explain how linear regression is used to predict continuous outcomes.
- The relationship between the independent (predictor) and dependent (response) variables
- The significance of the slope and intercept in the regression equation
- How well the model fits the data—often assessed using measures like r[2].

Explain how classifications techniques in supervised learning are used to predict discrete categorical outcomes.
- K-Nearest Neighbours (K-NN) and decision trees algorithms to categorize new data points, based on patterns learned from existing labelled data
- Real-world applications of K-NN may include collaborative filtering recommendation systems.
- Real-world applications of decision trees may include medical diagnosis based on a patient’s symptoms.

Explain the role of hyperparameter tuning when evaluating supervised learning algorithms.
- Accuracy, precision, recall and F1 score as evaluation metrics
- The role of hyperparameter tuning on model performance
- Overfitting and underfitting when training algorithms

Describe the application of genetic algorithms in various real-world situations.
- For example: population, fitness function, selection, crossover, mutation, evaluation, termination
- Real-world application: optimization problems such as route planning (travelling salesperson problem).

Outline the structure and function of ANNs and how multi-layer networks are used to model complex patterns in data sets.
- An artificial neural network (ANN) to simulate interconnected nodes or “neurons” to process and learn from input data, enabling tasks such as classification, regression and pattern recognition
- Sketch of a single perceptron, highlighting its input, weights, bias, activation function and output
- Sketch of a multi-layer perceptron (MLP) encompassing the input layer, one or more hidden layers and the output layer.

Discuss the ethical implications of machine learning in real-world scenarios.
- Ethical issues may include accountability, algorithmic fairness, bias, consent, environmental impact, privacy, security, societal impact, transparency.
- The challenges posed by biases in training data
- The ethics of using machine learning in online communication may include concerns about misinformation, bias, online harassment, anonymity, privacy.

Discuss ethical aspects of the increasing integration of computer technologies into daily life.
- The importance of continually reassessing ethical guidelines as technology advances
- The potential implications of emerging technologies such as quantum computing, augmented reality, virtual reality and the pervasive use of AI on society, individual rights, privacy and equity