AI Glossary: Letter "M"

Machine Learning is a branch of artificial intelligence focused on building systems that learn from data, identify patterns, and make decisions with minimal human intervention. It represents the broader field that includes deep learning and classical statistics.

Machine Translation (MT) is a subfield of computational linguistics focused on using artificial intelligence models to automatically translate text or speech from one human language to another.

Mamba is a sequence modeling architecture based on selective State Space Models (SSMs). It provides linear-time scaling relative to sequence length while matching or exceeding Transformer performance on language modeling, especially for long-context tasks.

Masked Language Modeling (MLM) is a self-supervised training task where a model learns token context by predicting hidden (masked) words in a sentence using surrounding left and right text tokens.

Max Pooling is a sample-based discretization process in CNNs. It divides the input image into sub-regions and outputs the maximum value from each sub-region, reducing dimensional size.

A Model Context Protocol Client (MCP Client) is an application (such as an IDE, chatbot, or developer platform) that implements the MCP protocol to discover, connect to, and invoke tools and data sources exposed by MCP servers.

A Model Context Protocol Server (MCP Server) is a lightweight utility service that exposes databases, file systems, specific APIs, or local command runtimes to MCP clients using a standardized, secure JSON protocol.

Mean Absolute Error (MAE) is a mathematical loss metric used in regression models that calculates the average absolute differences between predicted values and actual target values.

Microsoft Azure AI is a comprehensive enterprise cloud platform offering managed infrastructure, model APIs, OpenAI service deployments, and MLOps tooling for enterprise AI applications.

Mistral AI is a leading European artificial intelligence research company specializing in high-efficiency open-weights models, mixture-of-experts architectures, and enterprise AI deployments.

Mixture of Agents (MoA) is an architectural pattern that aggregates outputs from multiple Large Language Models (LLMs) or sub-agents to produce a superior unified response. By utilizing a layered approach where different models act as generators and aggregators, MoA achieves higher accuracy and reasoning quality than any single constituent model.

Mixture of Depths (MoD) is a compute optimization technique where models dynamically route and process only a fraction of tokens through specific layers, skipping computation for simpler tokens.

Mixture of Experts (MoE) is a neural network design that scales model parameters without increasing compute cost. Instead of activating the entire network for every token, MoE routes inputs to specialized sub-networks ("experts") using a gating router.

MLOps (Machine Learning Operations) is a set of practices, culture, and tools focused on automating and unifying the lifecycle of machine learning models, spanning data collection, training, testing, deployment, and monitoring.

Model Collapse is a degenerative process affecting generative AI models trained recursively on synthetic data generated by previous generations of AI models. Over iterations, the model loses diversity, starts repeating patterns, and eventually outputs garbage.

Model Context Protocol (MCP) is an open-source standard created by Anthropic that enables AI applications and agents to connect securely to local or remote data sources, developer tools, and API services via a standardized protocol.

Model Drift (or model decay) is the degradation of an AI model's predictive performance in production over time, caused by changes in the statistical properties of real-world input data relative to the training data.

Model Merging is the process of combining two or more fine-tuned models into a single model without running any retraining or compute-heavy tuning. It averages or mathematically blends the weight metrics of the models.

Model Pruning is a model compression technique that removes non-essential weights or neurons from a trained network. By zeroing out parameters that have minimal impact on output predictions, it reduces model file sizes and execution latency.

A Model Registry is a centralized repository store for managing the lifecycle of machine learning models. It stores model weights, parameter logs, version details, and deployment states.

Multi-Agent Orchestration is the protocol framework that defines how multiple specialized AI agents communicate, delegate sub-tasks, exchange context, and collaborate sequentially or hierarchically to achieve a collective goal.

A Multi-Agent System (MAS) is a computerized system composed of multiple interacting intelligent agents. These agents coordinate, communicate, and collaborate (or compete) with each other to solve complex problems that are beyond the individual capabilities of any single agent.

Multi-Head Attention is an attention layout in Transformers that splits query, key, and value vectors into multiple subspaces, allowing the model to attend to information from different representation coordinates simultaneously.

Multi-head Latent Attention (MLA) is a memory-efficient attention mechanism that compresses Key-Value (KV) vectors into a low-rank joint latent space during inference, dramatically reducing KV cache memory footprint while maintaining full Multi-Head Attention modeling capacity.

Multi-Query Attention (MQA) is an attention architecture where all query heads share a single Key and Value head to minimize KV cache storage.

Multimodal AI refers to systems capable of processing, understanding, and generating multiple types of input and output data modalities simultaneously, such as text, images, audio, video, and code. This mirrors human-like perception across sensory channels.