Glossary Reference
Azure Services
Azure CLI
A command-line interface tool that provides a set of commands for managing Azure resources from the terminal or command prompt.
Azure Portal
A web-based interface for managing, monitoring, and configuring Azure resources and services through a graphical user interface.
Blob Storage
Azure's object storage solution optimised for storing massive amounts of unstructured data, such as text, images, videos, and documents.
Deployment
The process of making an application, service, or resource available and operational in Azure.
Endpoint
A URL that provides access to a deployed model or service for making predictions or retrieving data.
Region
A geographical area containing one or more Azure data centres, used to provide services with low latency and data residency compliance.
Resource
A manageable item in Azure, such as a virtual machine, storage account, web app, database, or virtual network.
Resource Group
A container that holds related Azure resources for easier management and organisation.
Subscription
A logical unit of Azure services that is linked to an Azure account and used for billing purposes.
Tenant
A dedicated instance of Azure Active Directory that represents an organisation and manages user identities and access permissions.
AI & Machine Learning
Agent
An AI system that can perceive its environment, make decisions, and take actions to achieve specific goals autonomously.
Artificial Intelligence (AI)
Computing alogorithms that are adaptable, developing new ways of finding patterns in data beyond their original programming through training and learning. AI can often be autonomous, making decisions without direct human control.
Backpropagation
A learning algorithm used to train neural networks by calculating gradients and adjusting weights to minimise error.
Batch
A subset of training data processed together during one iteration of model training, helping to improve efficiency and stability.
Bias
In machine learning this can refer to the error between a prediction and the true value. It can also refer to the inherent prejudices in a training dataset.
Classification
A machine learning task that involves predicting discrete categories or classes for input data.
Computer Vision
A field of AI that enables computers to interpret and understand visual information from images and videos.
Deep Learning
A subset of machine learning that uses neural networks with multiple layers to learn complex patterns in data.
Embedding
Converting words, phrases, or other data into numerical vector representations that capture semantic meaning.
Epoch
One complete pass through the entire training dataset during the model training process.
Fine-tuning
Adjusting a pre-trained model for specific tasks by training it further on domain-specific data.
Generative AI
AI systems that can create new content, including text, images, code, or other media, based on patterns learnt from training data.
Learning Rate
A parameter that controls how quickly a model adjusts its weights during training to minimise errors.
LLM (Large Language Model)
A type of AI model trained on vast amounts of text data to understand and generate human-like language responses.
Machine Learning
A subset of AI that uses algorithms and models to learn a dataset through training, typically for prediction. Machine learning is often used interchangeably with AI.
Model
A trained algorithm that makes predictions or decisions based on patterns learnt from data.
Neural Network
A computing system inspired by biological neural networks, consisting of interconnected nodes that process information.
Overfitting
When a model learns training data too specifically and fails to generalise well to new, unseen data.
Regression
A machine learning task that involves predicting continuous numerical values rather than discrete categories.
Supervised Learning
Machine learning approach where models learn from labelled examples with known correct answers.
Tokenisation
The process of breaking down text into smaller units (words, subwords, or characters) for AI processing.
Training Data
Dataset used to teach the model patterns and relationships during the learning process.
Transfer Learning
Using knowledge gained from one task to improve learning and performance on a related but different task.
Transformer
A neural network architecture that uses attention mechanisms to process sequential data, particularly effective for language tasks.
Unsupervised Learning
Machine learning approach that finds patterns and relationships in data without labelled examples or known outcomes.
Validation Data
Dataset used to tune model parameters and evaluate performance during training without affecting the final test.
Computing Terminology
Compute
The processing power and computational resources provided by cloud services to run applications and workloads.
Virtual Machines
Computing environments that function as virtual computer systems with their own CPU, memory, network interface, and storage.
Machine Clusters
Groups of connected computers that work together as a single system to provide increased computational power and reliability.
Scalability
The ability to increase or decrease computing resources based on demand.
Virtual Network
A software-defined network that enables secure communication between cloud resources and on-premises infrastructure.
Compute Architecture
The design and structure of computing systems, including how processors, memory, and other components work together.
OS Disk
The primary storage disk that contains the operating system and system files for a virtual machine.
OS Image
A pre-configured template containing an operating system and software that can be used to create virtual machines.
SSH (Secure Shell)
A secure protocol for remotely accessing and managing computers over a network.
Ports
Virtual endpoints that allow different applications and services to communicate through a network.
IP Address
A unique numerical identifier assigned to devices on a network to enable communication.
CPU (Central Processing Unit)
The main processor of a computer that executes instructions and performs calculations.
GPU (Graphics Processing Unit)
A specialized processor designed for parallel processing, particularly useful for AI, machine learning, and graphics tasks.
Public Key/Private Key
A cryptographic key pair used for secure authentication, where the public key can be shared while the private key remains secret.
SSD/HDD
Storage devices - Solid State Drives (faster, no moving parts) and Hard Disk Drives (traditional spinning disk storage).
Firewall
A security system that monitors and controls network traffic based on predetermined security rules.
RAM/Memory
Random Access Memory - temporary storage used by computers to hold data and programs currently in use.