AI & Machine Learning

Machine learning and deep learning fundamentals, LLMs and generative AI, RAG, AI agents and their protocols, evaluation, guardrails and responsible AI, computer vision, speech and efficient inference on edge hardware.

Where AiVibe comes in

AiVibe delivers AI and machine learning services, chatbots and virtual assistants with RAG, MCP tools and voice, AI quality management including bias detection and model validation, and the AIMURUGA AI agent, and builds Intel-based edge AI devices using the Intel Distribution of OpenVINO toolkit.

Explore AiVibe’s work in AI & Machine Learning →

60 terms

Agent2Agent Protocol (A2A)Agent2Agent (A2A) is an open protocol, announced by Google in 2025 and later contributed to the Linux Foundation, that lets AI agents…
Agentic AIAgentic AI describes AI systems designed to act with a degree of autonomy towards goals, planning and executing multi-step tasks with…
AI AgentAn AI agent is a software system that uses an AI model, typically a large language model, to pursue a goal by planning steps, calling…
AI BiasAI bias is systematic error in an AI system's outputs that unfairly favours or disadvantages certain groups, conditions or cases, usually…
AI GuardrailsAI guardrails are technical and procedural controls that keep an AI system's inputs, outputs and actions within defined limits, for…
AI HallucinationAn AI hallucination is output from a generative model that is fluent and plausible but factually incorrect, unsupported by its sources or…
AI InferenceAI inference is the stage at which a trained model is used to make predictions or generate outputs on new data, as distinct from training…
Anomaly DetectionAnomaly detection identifies data points, events or patterns that deviate significantly from expected behaviour, such as unusual machine…
Artificial Neural NetworkAn artificial neural network is a machine learning model built from layers of interconnected units, loosely inspired by biological…
Automatic Speech Recognition (ASR)Automatic speech recognition (ASR), or speech-to-text, converts spoken language into written text using neural acoustic and language…
Computer VisionComputer vision is the field of AI that enables computers to interpret images and video, performing tasks such as classifying images…
Context WindowThe context window is the maximum number of tokens a language model can consider at once, covering the system prompt, conversation…
Conversational AIConversational AI is technology that lets people interact with software in natural language, by text or voice, through chatbots and…
Convolutional Neural Network (CNN)A convolutional neural network (CNN) is a deep learning architecture that applies learned filters across an image or signal, detecting…
Data Annotation (Data Labelling)Data annotation, or labelling, is the process of adding correct answers to raw data, such as class labels, bounding boxes, segmentation…
Deep LearningDeep learning is a subset of machine learning that uses neural networks with many layers to learn representations directly from raw data…
Diffusion ModelA diffusion model is a generative model that learns to reverse a gradual noising process: starting from random noise, it removes noise…
Edge AIEdge AI runs machine learning inference on devices close to where data is produced, such as cameras, gateways, industrial PCs and…
Embeddings (Vector Embeddings)An embedding is a list of numbers, a vector, that represents text, an image or other data so that items with similar meaning lie close…
Explainable AI (XAI)Explainable AI (XAI) covers methods that make the decisions of machine learning models understandable to people, showing which inputs…
Fine-TuningFine-tuning continues training a pre-trained model on a smaller, task-specific dataset so that it adapts to a particular domain, style or…
Foundation ModelA foundation model is a large model trained on broad data, usually with self-supervised learning, that can be adapted to many downstream…
Function Calling (Tool Use)Function calling, or tool use, lets a language model request that an application run a defined function, such as a database query or API…
Generative AIGenerative AI refers to models that create new content, such as text, images, audio, video, code or 3D data, by learning the patterns in…
Graphics Processing Unit (GPU) for AIA graphics processing unit (GPU) is a processor with many parallel cores, originally designed for rendering graphics, that has become the…
Grounding (AI)Grounding means anchoring an AI model's outputs in verifiable sources, such as retrieved documents, databases, sensor readings or search…
Image ClassificationImage classification is the computer vision task of assigning one or more labels to an entire image, such as good or defective, or the…
Image SegmentationImage segmentation is the computer vision task of classifying every pixel in an image, producing masks that outline the exact shape and…
Knowledge DistillationKnowledge distillation trains a smaller student model to reproduce the behaviour of a larger teacher model, transferring much of the…
Large Language Model (LLM)A large language model (LLM) is a neural network, usually a transformer, trained on very large text collections to predict the next token…
LLM EvaluationLLM evaluation assesses the quality, accuracy, safety and reliability of large language models and the applications built on them, using…
Machine Learning (ML)Machine learning is a branch of artificial intelligence in which systems learn patterns from data to make predictions or decisions…
MLOpsMLOps applies DevOps principles to machine learning, combining practices and tools to version data and models, automate training and…
Model Context Protocol (MCP)The Model Context Protocol (MCP) is an open protocol, introduced by Anthropic in 2024, that standardises how AI applications connect to…
Model Drift (Data and Concept Drift)Model drift is the decline in a deployed model's performance over time because the data it sees changes, known as data drift, or because…
Model EvaluationModel evaluation measures how well a machine learning model performs on data it has not seen during training, using metrics suited to the…
Model QuantisationModel quantisation reduces the numerical precision of a neural network's weights and activations, for example from 32-bit floating point…
Multi-Agent SystemA multi-agent system is a set of AI agents that work together, or sometimes compete, on a task, each with its own role, tools or…
Natural Language Processing (NLP)Natural language processing (NLP) is the field of AI concerned with enabling computers to understand, interpret and generate human…
Neural Processing Unit (NPU)A neural processing unit (NPU) is a processor or processor block designed specifically to accelerate neural network inference…
Object DetectionObject detection is the computer vision task of finding each object of interest in an image, drawing a bounding box around it and…
Open Neural Network Exchange (ONNX)ONNX (Open Neural Network Exchange) is an open format for representing machine learning models, which lets a model trained in one…
OpenVINO ToolkitOpenVINO is an open-source toolkit from Intel for optimising and deploying AI inference, converting models from frameworks such as…
Optical Character Recognition (OCR)Optical character recognition (OCR) converts images of printed or handwritten text into machine-readable characters, and is used to read…
Overfitting and UnderfittingOverfitting occurs when a model learns the noise and peculiarities of its training data, performing well in training but poorly on new…
Prompt EngineeringPrompt engineering is the practice of designing the instructions, context and examples given to a language model so that it produces…
Prompt InjectionPrompt injection is an attack in which crafted text causes a language model to ignore its intended instructions and follow an attacker's…
Reinforcement Learning from Human Feedback (RLHF)Reinforcement learning from human feedback (RLHF) aligns a model's behaviour with human preferences: people compare model outputs, a…
Responsible AIResponsible AI is the practice of designing, developing and operating AI systems so that they are lawful, safe, fair, transparent…
Retrieval-Augmented Generation (RAG)Retrieval-augmented generation (RAG) improves a language model's answers by first retrieving relevant passages from a trusted knowledge…
Supervised LearningSupervised learning trains a model on labelled examples, pairs of inputs and correct outputs, so that it learns to predict the output for…
Synthetic DataSynthetic data is artificially generated data, created by simulation, rendering, rules or generative models, that mimics the properties of…
Text-to-Speech (Speech Synthesis)Text-to-speech (TTS), or speech synthesis, converts written text into spoken audio, giving a voice to assistants, navigation systems…
Tokens and Tokenisation (LLMs)In language models, tokenisation splits text into tokens, units such as words, word fragments or characters, each mapped to an integer ID.…
TOPS (Tera Operations Per Second)TOPS, or tera operations per second, is a measure of an AI accelerator's peak compute throughput: one TOPS equals one trillion operations…
Transfer LearningTransfer learning reuses a model trained on one task or dataset as the starting point for a related task, so that a new model can be…
Transformer (Neural Network Architecture)The transformer is a neural network architecture based on self-attention, which lets every element of a sequence weigh its relationship to…
Unsupervised LearningUnsupervised learning finds structure in data without labelled answers, for example grouping similar items with clustering, reducing many…
Vector DatabaseA vector database stores embeddings alongside their source data and metadata and quickly retrieves the vectors most similar to a query…
Vision-Language Model (VLM)A vision-language model (VLM) is a multimodal model that processes images together with text, so that it can describe images, answer…

AI & Machine Learning

Where AiVibe comes in

60 terms

Other topics