IB Computer Science HL (Case Study 2025)

All 2025 case study terms for IB Computer Science. Imported from computersciencecafe.com

Backpropagation through time (BPTT)

A variant of the backpropagation algorithm used for training Recurrent Neural Networks (RNNs), where gradients are propagated backward through time to update the weights.

Bag-of-words

A model used in natural language processing where text is represented as an unordered collection of words, disregarding grammar and word order but keeping track of word frequency.

Biases

Systematic errors in data or algorithms that can lead to unfair or discriminatory outcomes. Biases can occur in various forms, including confirmation, historical, labeling, linguistic, sampling, and selection biases.

Confirmation Bias

A type of bias where data is skewed towards a particular viewpoint or expected outcome, often reinforcing pre-existing beliefs.

Historical Bias

A bias that occurs when training data reflects outdated or historical patterns that may not be relevant to current scenarios, potentially leading to inaccurate predictions.

Labelling Bias

Occurs when the labels applied to training data are subjective, inaccurate, or incomplete, affecting the model's ability to learn correctly.

Linguistic Bias

Bias resulting from training data that favors certain dialects, vocabularies, or linguistic styles, potentially disadvantaging users who use different linguistic forms.

Sampling Bias

Occurs when the training dataset is not representative of the entire population, leading to a model that performs well for certain groups but poorly for others.

Selection Bias

Bias introduced when the training data is not randomly selected but chosen based on specific criteria, potentially missing important variations.

Dataset

A collection of data used to train and evaluate machine learning models. A good dataset is diverse, high-quality, relevant, and up-to-date.

Deep Learning

A subset of machine learning involving neural networks with many layers (deep neural networks) that can learn complex patterns in large datasets.

Graphical Processing Unit (GPU)

Specialised hardware designed to accelerate the processing of large-scale data and complex computations, particularly useful for parallel processing in machine learning tasks.

Hyperparameter Tuning

The process of optimizing the parameters that govern the training of a machine learning model (e.g., learning rate, number of layers) to improve its performance.

Large Language Model (LLM)

Advanced neural networks trained on vast amounts of text data to understand and generate human-like language, such as GPT-3 and Microsoft Co-pilot.

Latency

The delay between a user's query and the chatbot's response. High latency can negatively impact user experience by making the chatbot seem slow.

Long Short-Term Memory (LSTM)

A type of RNN designed to overcome the vanishing gradient problem, using a gating mechanism to retain or forget information over time, enabling the learning of long-term dependencies.

Loss Function

A mathematical function that measures the difference between the predicted output of a model and the actual target output, guiding the optimization process during training.

Memory Cell State

In LSTM networks, the memory cell state represents the information that flows through the network, controlled by input, forget, and output gates to manage long-term dependencies.

Natural Language Processing (NLP)

The field of AI focused on enabling machines to understand, interpret, and generate human language.

Discourse Integration

A stage in NLP where the meaning of a sentence is integrated with the larger context of the conversation to generate coherent and contextually appropriate responses.

Lexical Analysis

The process of breaking down text into individual words and sentences, identifying parts of speech, and preparing it for further processing.

Pragmatic Analysis

Analysing the social, legal, and cultural context of a sentence to understand its intended meaning and implications.

Semantic Analysis

The process of understanding the meaning of words and sentences, going beyond the surface-level structure to interpret the underlying concepts.

Syntactical Analysis (Parsing)

Analysing the grammatical structure of a sentence, identifying the relationships between words and phrases.

Natural Language Understanding (NLU)

A component of NLP focused on understanding the user's input by analysing linguistic features and context.

Pre-processing

The initial step in data preparation, involving cleaning, transforming, and reducing data to improve its quality and make it suitable for training machine learning models.

Recurrent Neural Network (RNN)

A type of neural network designed to handle sequential data, maintaining memory of previous inputs through hidden states to process sequences of data.

Self-Attention Mechanism

A technique in transformer neural networks that captures relationships between different words in a sequence by computing attention weights, enabling better handling of long-term dependencies.

Synthetic Data

Artificially generated data used to supplement real data, covering scenarios that may not be well-represented in the original dataset.

Tensor Processing Unit (TPU)

Custom hardware developed by Google specifically designed to accelerate machine learning workloads, particularly for deep learning models.

Transformer Neural Network (Transformer NN)

A type of neural network that uses a self-attention mechanism for parallel processing of data, particularly effective for natural language processing tasks.

Vanishing Gradient

A problem in training deep neural networks where gradients become very small, making it difficult to update the weights effectively and learn long-term dependencies.

Weights

Parameters in a neural network that are adjusted during training to minimize the loss function and improve the model's predictions.