Glossary

From Our Knowledge Base

Welcome to the Augmetrics® AI Glossary, where clarity meets capability.

We’ve defined the most important AI terms in plain language—organized for quick access and real-world understanding.

Whether you’re new to AI or deep in deployment, this glossary is your go-to reference for cutting through the noise.

To make it even easier to navigate, we’ve grouped entries into key categories like Compute & Processing, AI Fundamentals, Sustainability, Comparisons & Tradeoffs, and Inference & Deployment—so you can find exactly what you need, faster.

Jump to:


Compute & AI Processing Definitions

This section covers the nuts and bolts of how AI models are trained, optimized, and deployed—from GPUs and TPUs to key algorithms like gradient descent and backpropagation.

If it powers the AI engine, you’ll find it here.

What is AI Inference?
AI Inference is the phase where a trained model generates predictions or outputs from new input data. It’s often the most compute-intensive and cost-sensitive part of deployment.

What is AI Training?
AI Training is the process where a model learns from data by adjusting internal weights to improve prediction accuracy through repeated optimization.

What is a GPU compared to a TPU?
A GPU (Graphics Processing Unit) is optimized for parallel processing and widely used in AI training. A TPU (Tensor Processing Unit) is a custom chip by Google designed specifically to accelerate machine learning.

What is Backpropagation?
Backpropagation is an algorithm that adjusts neural network weights by calculating and distributing errors backward through the model after each prediction.

What is Gradient Descent?
Gradient Descent is an optimization technique used to minimize a model’s error by iteratively updating weights based on the slope of the loss function.

What is the Cost of Delivery in AI?
The Cost of Delivery refers to the energy, infrastructure, and compute resources required to serve AI outputs in real-time, including inference compute, bandwidth, and storage.

Post-Preprocessing Stage: What It Means & What It Does

Once raw data has been cleaned, normalized, and structured during pre-processing, the next step is…Read Article


Inference & Deployment

From embeddings to explainability and real-time prediction costs, this category focuses on what happens when the model goes live.

If it impacts speed, trust, or performance at scale, you’ll find it here.

What is Embedding in AI?
An Embedding is a numerical representation of text, image, or other data that preserves semantic meaning—used to power search, recommendations, and similarity comparisons.

What is Explainability in AI?
Explainability refers to understanding how and why an AI made a decision, increasing transparency and trust—especially in regulated or high-stakes settings.

What is Bias in AI?
Bias in AI refers to unfair patterns in model outputs caused by skewed or incomplete training data.

What is Attribution?
Attribution tracks the influence of specific inputs, data sources, or model components on a given AI output—used in auditing, compliance, and model debugging.


AI Fundamentals Definitions

Here’s where you’ll find the core concepts behind AI systems, from neural networks to language models and the math that drives them.

It’s the essential vocabulary for anyone working with—or learning about—modern AI.

What is a Neural Network?
A Neural Network is a layered model inspired by the human brain, built from artificial neurons that process data and learn patterns.

What is a Large Language Model (LLM)?
An LLM is an AI system trained on vast text corpora to understand, predict, and generate human-like language for tasks like chat, summarization, and Q&A.

What is an Activation Function?
An Activation Function controls whether a neuron in a neural network should ‘fire’ based on its input, enabling non-linear decision-making.

What is an Epoch in AI Training?
An Epoch is one complete pass through the entire training dataset. Multiple epochs are often used to improve model accuracy.

What is a Loss Function?
A Loss Function measures the gap between predicted and actual values, guiding model optimization during training.

What is a Token in NLP?
A Token is the smallest unit of text processed by a language model—usually a word, subword, or character depending on the tokenizer used.


Sustainability Definitions

AI has a compute problem—and this section explains how smarter training, model compression, and transfer learning can help solve it.

Explore the strategies that improve performance while reducing waste, cost, and energy consumption.

What is Pre-Processing?
Pre-Processing is the stage where raw data is cleaned and structured before training. It includes normalization, tokenization, and removing duplicates.

Pre-Processing Stage

Pre-processing is the critical first step in preparing raw data for AI model training, ensuring…Read Article

What is Model Compression?
Model Compression reduces the size of an AI model to improve efficiency, speed up inference, and enable deployment on smaller devices.

What is Fine-Tuning?
Fine-Tuning adjusts a pre-trained model using new, domain-specific data to improve accuracy for a specific task without retraining from scratch.

What is Transfer Learning?
Transfer Learning reuses knowledge from a model trained on one task and applies it to a new task—saving time, compute, and data.


Comparisons & Tradeoffs

Understanding AI means understanding its choices—this section breaks down the differences between model types, training styles, and task-specific strategies.

Think of it as your side-by-side guide to what works, when, and why.

What is Overfitting vs. Underfitting?
Overfitting happens when a model learns training data too precisely and fails to generalize. Underfitting occurs when a model is too simplistic and misses important patterns.

What is Supervised Learning vs. Unsupervised Learning?
Supervised Learning uses labeled data to train a model, while Unsupervised Learning finds patterns in unlabeled data, often for clustering or anomaly detection.

What is a CNN compared to an RNN?
CNNs are designed for spatial data like images; RNNs process sequential data like text or time series.

What is Named Entity Recognition (NER) vs. Sentiment Analysis?
NER identifies and categorizes names (people, places, orgs); Sentiment Analysis determines emotional tone (positive, negative, neutral) in text.

What is Speech-to-Text vs. Text-to-Speech?
Speech-to-Text converts spoken audio into written words. Text-to-Speech does the reverse, turning text into synthesized voice.

What is a Pre-Trained Model vs. a Custom Model?
A Pre-Trained Model is trained on general data and can be adapted for new use cases. A Custom Model is built and trained from scratch for a specific task.


We want to hear from you.

We know that Augmetrics® is not a universal solution to sustainability problems that we face, but we also know it is a start; one that took over 10 years to develop.