AI & Machine Learning Terms

Essential terminology for Artificial Intelligence, Machine Learning, Deep Learning, and related technologies.

A

Accuracy

A metric measuring the proportion of correct predictions made by a model out of all predictions.

Agent

An entity that perceives its environment through sensors and acts upon that environment through actuators.

Algorithm

A step-by-step procedure or set of rules for solving a problem or performing a computation in AI/ML.

Artificial Intelligence (AI)

The simulation of human intelligence in machines programmed to think, learn, and problem-solve.

Artificial Neural Network (ANN)

A computing system inspired by biological neural networks, consisting of interconnected nodes (neurons) that process information.

B

Backpropagation

An algorithm for training neural networks by calculating gradients and adjusting weights to minimize error.

Bias

In ML, a systematic error introduced by the model’s assumptions; also refers to a parameter in neural networks that helps fit data better.

Big Data

Extremely large datasets that require specialized tools and techniques for storage, processing, and analysis.

C

Classification

A supervised learning task where the model predicts discrete class labels for input data.

Clustering

An unsupervised learning technique that groups similar data points together based on their characteristics.

Computer Vision

A field of AI that enables computers to interpret and understand visual information from the world.

Convolutional Neural Network (CNN)

A deep learning architecture specialized for processing grid-like data such as images.

D

Data Augmentation

Techniques for artificially increasing the size and diversity of training data by applying transformations.

Deep Learning

A subset of machine learning using neural networks with multiple layers to learn hierarchical representations of data.

Dimensionality Reduction

Techniques for reducing the number of features in a dataset while preserving important information.

E

Embedding

A representation of data (text, images) in a lower-dimensional continuous vector space, capturing semantic relationships.

Epoch

One complete pass through the entire training dataset during model training.

Evaluation Metrics

Quantitative measures used to assess model performance (accuracy, precision, recall, F1-score, etc.).

F

Feature

An individual measurable property or characteristic of a phenomenon being observed, used as input for ML models.

Feature Engineering

The process of creating new features or transforming existing ones to improve model performance.

Fine-Tuning

The process of adapting a pre-trained model to a specific task by continuing training on task-specific data.

G

Generative AI

AI systems that can create new content (text, images, music, code) based on training data.

Gradient Descent

An optimization algorithm that iteratively adjusts model parameters to minimize the loss function.

H

Hallucination

When an AI model generates plausible-sounding but incorrect or nonsensical information.

Hyperparameter

Configuration settings for ML algorithms that are set before training begins (learning rate, batch size, number of layers).

I

Inference

The process of using a trained model to make predictions on new, unseen data.

Interpretability

The degree to which humans can understand and explain the decisions made by an ML model.

L

Label

The output or target variable in supervised learning that the model is trained to predict.

Large Language Model (LLM)

A type of AI model trained on vast amounts of text data to understand and generate human-like text.

Learning Rate

A hyperparameter that controls how much model weights are adjusted during training.

Loss Function

A mathematical function that measures how well a model’s predictions match the actual values.

M

Machine Learning (ML)

A subset of AI that enables systems to learn and improve from experience without being explicitly programmed.

Model

A mathematical representation trained on data to make predictions or decisions.

Model Training

The process of learning patterns from data by adjusting model parameters to minimize error.

N

Natural Language Processing (NLP)

A field of AI focused on enabling computers to understand, interpret, and generate human language.

Neural Network

A computational model inspired by the human brain’s structure and function, consisting of interconnected nodes.

O

Overfitting

When a model learns training data too well, including noise, resulting in poor performance on new data.

Optimization

The process of finding the best parameters for a model to minimize error or maximize performance.

P

Perceptron

The simplest form of a neural network, consisting of a single neuron that makes binary decisions.

Precision

A metric measuring the proportion of true positive predictions out of all positive predictions made.

Pre-trained Model

A model that has already been trained on a large dataset and can be fine-tuned or used for transfer learning.

Prompt

Input text or instructions given to a language model to generate a specific response or perform a task.

Prompt Engineering

The practice of crafting effective prompts to get desired outputs from AI models, especially LLMs.

R

Recall

A metric measuring the proportion of true positive predictions out of all actual positive instances.

Recurrent Neural Network (RNN)

A neural network architecture designed for sequential data, with connections that form cycles.

Regression

A supervised learning task where the model predicts continuous numerical values.

Reinforcement Learning

A learning paradigm where an agent learns to make decisions by receiving rewards or penalties for actions.

Retrieval-Augmented Generation (RAG)

A technique combining information retrieval with generative models to produce more accurate and grounded responses.

S

Supervised Learning

A learning approach where models are trained on labeled data with known input-output pairs.

Support Vector Machine (SVM)

A supervised learning algorithm used for classification and regression tasks.

T

Training Data

The dataset used to train a machine learning model, consisting of input features and corresponding labels.

Transfer Learning

A technique where a model trained on one task is adapted for a different but related task.

Transformer

A deep learning architecture based on attention mechanisms, fundamental to modern NLP models like GPT and BERT.

U

Underfitting

When a model is too simple to capture the underlying patterns in data, resulting in poor performance.

Unsupervised Learning

A learning approach where models find patterns in data without labeled outputs.

V

Validation Set

A subset of data used to evaluate model performance during training and tune hyperparameters.

Variance

The amount by which model predictions vary when trained on different datasets.

W

Weight

A parameter in neural networks that represents the strength of connection between neurons, adjusted during training.

---

These AI and ML terms provide a foundation for understanding modern artificial intelligence and machine learning technologies.