AI Basics & Terminology

AI Terminology Challenge

AI Basics & Terminology par exactly 5 practice questions.

AI Ethics & Safety

AI Basics & Terminology par exactly 5 practice questions.

AI Evaluation

AI Basics & Terminology par exactly 5 practice questions.

Generative AI

AI Basics & Terminology par exactly 5 practice questions.

Neural Networks

AI Basics & Terminology par exactly 5 practice questions.

Machine Learning Types

AI Basics & Terminology par exactly 5 practice questions.

AI Fundamentals

AI Basics & Terminology par exactly 5 practice questions.

AI Ethics, Bias and Limitations

Algorithmic bias, the black box problem, deepfakes and training-data privacy.

As AI systems make consequential decisions, questions of fairness, explainability and consent have moved from academic discussion to regulation. This quiz covers algorithmic bias, the difficulty of explaining model decisions, synthetic media and the contested question of where training data comes from.

Natural Language Processing Concepts

Tokenization, named entity recognition and the architecture that replaced recurrent networks.

Natural language processing covers everything from splitting text into units to extracting meaning from it. The field changed shape after 2017, when attention-based architectures replaced sequential processing. This quiz covers both the classical preprocessing vocabulary and the modern architectural shift.

Classical Algorithms in Machine Learning

Random forests, Naive Bayes, support vector machines and the confusion matrix.

Before deep learning dominated, a set of statistical algorithms carried most practical machine learning work, and they remain the right choice for small structured datasets. This quiz covers ensemble methods, probabilistic classifiers, margin-based classification and the confusion matrix used to evaluate them all.

Applied Machine Learning Concepts

Transfer learning, validation sets and the tradeoffs practitioners manage every day.

Practical machine learning is mostly about managing tradeoffs: between model complexity and generalisation, between training cost and accuracy, and between general and specialised models. This quiz covers transfer learning, fine-tuning, data splitting and the bias-variance tradeoff that underlies all of them.

AI Pioneers and Major Awards

Turing Award winners, Nobel laureates and the datasets that changed computer vision.

The recognition of deep learning by the 2018 Turing Award marked the field's move from a niche approach to the mainstream of computer science. This quiz covers the researchers behind that shift, the awards that recognise them, and the datasets and systems that made their case.

Modern AI Systems and Language Models

Tokens, embeddings, hallucination and the vocabulary of large language models.

Large language models introduced a vocabulary that is now common in mainstream reporting: tokens, embeddings, pre-training and hallucination. Each term has a precise technical meaning that is often blurred in popular coverage. This quiz covers those definitions along with the 2012 result that started the deep learning boom.

AI Model Metrics and Training Terms

Precision, recall, epochs and learning rates: the vocabulary of evaluating and training models.

Accuracy alone is a poor measure of a model, particularly when classes are imbalanced. Precision, recall and their harmonic mean are the standard alternatives. This quiz also covers the core training vocabulary of epochs, batches and learning rates that appears in every practical machine learning workflow.

Neural Networks and Deep Learning

Layers, backpropagation and the architectures behind image and language models.

Deep learning uses neural networks with many stacked layers, trained by propagating error backwards through those layers. Different architectures suit different data: convolutional networks for images, and since 2017 transformers for sequences. This quiz covers the mechanisms and the landmark architectures.

Machine Learning Basics Explained

Supervised, unsupervised and reinforcement learning, and the failure modes that come with each.

Machine learning is usually divided into three families defined by what the algorithm is given: labelled examples, unlabelled data, or a reward signal. Understanding this split, and the common failure of overfitting, is the starting point for all further study in the field.

Foundations of Artificial Intelligence

The people, papers and milestone machines that established artificial intelligence as a field.

Artificial intelligence became a named discipline at the Dartmouth Conference of 1956, but its central question was posed six years earlier by Alan Turing. This quiz covers the founding figures, the naming of the field, and the landmark machine victories that brought AI into public awareness.

AI Basics & Terminology Quiz

Test your knowledge of fundamental AI concepts and terminology.

This quiz covers essential AI terminology, including key concepts like machine learning, neural networks, natural language processing, and ethical considerations. It aims to reinforce foundational knowledge required for advanced AI studies and applications.

AI Basics & Terminology Quiz

Test your knowledge of fundamental AI concepts and terminology.

This quiz covers essential AI terminology, including key concepts like machine learning, neural networks, natural language processing, and AI ethics. It provides a foundational understanding of how AI systems are designed and implemented.

AI Basics & Terminology Quiz

Test your knowledge of fundamental AI concepts and terminology.

This quiz covers essential AI concepts such as machine learning, neural networks, natural language processing, and key AI terminology. It provides a foundational understanding of AI technologies and their applications.