AI Glossary

This glossary contains key terms and concepts you need to understand the workings of AI systems.

A

Artificial Intelligence (AI): The simulation of human intelligence in machines that are programmed to think and learn.
Algorithm: A set of rules or steps for solving a problem or performing a task, often implemented in computer programming.
ANN: Artificial Neural Network – A model inspired by the structure of the human brain, used in machine learning.

Bias: Systematic errors in a machine learning model that can result in unfair or incorrect outcomes.
BERT: Bidirectional Encoder Representations from Transformers – A state-of-the-art NLP model developed by Google.
BLEU: Bilingual Evaluation Understudy – A metric for evaluating the quality of machine-translated text.

CNN: Convolutional Neural Network – A type of neural network commonly used for image recognition and processing.
CV: Computer Vision – A field of AI focused on visual data processing and interpretation.

Deep Learning (DL): A subset of machine learning involving neural networks with many layers to model complex patterns in data.
Data Preprocessing: The process of cleaning, transforming, and organizing data before it is used to train a model.
DNN: Deep Neural Network – Neural networks with multiple layers of nodes.

Explainable AI (XAI): Techniques and methods that make the decision-making processes of AI systems interpretable to humans.

Feature: An individual measurable property or characteristic of a dataset used in machine learning.
FM: Foundation Model – A large pre-trained AI model, like GPT or BERT, which can be fine-tuned for specific tasks.
FLOPS: Floating Point Operations Per Second – A measure of computational performance.

Generative AI (Gen AI): A type of AI that creates new data, such as text, images, or music, based on learned patterns.
Gradient Descent: An optimization algorithm used to minimize a loss function by iteratively adjusting model parameters.
GAN: Generative Adversarial Network – A type of neural network used to generate realistic data, such as images or audio.
GPT: Generative Pre-trained Transformer – A type of large language model (LLM) developed by OpenAI.

Hyperparameters: Settings or configurations used to control the training process of a machine learning model.

Inference: The process of using a trained machine learning model to make predictions or decisions on new data.

Loss Function: A mathematical function used to evaluate how well a machine learning model is performing.
LLM: Large Language Model – AI models trained on massive text datasets to understand and generate human-like language.
LSTM: Long Short-Term Memory – A type of recurrent neural network (RNN) designed to handle sequential data.

Machine Learning (ML): A subset of AI focused on building systems that can learn from and make decisions based on data.
MLP: Multilayer Perceptron – A type of feedforward neural network with multiple layers.

Neural Network (NN): A computational model inspired by the human brain, consisting of interconnected nodes (neurons) organized into layers.
Natural Language Processing (NLP): A field of AI that focuses on the interaction between computers and human languages.
NLG: Natural Language Generation – The process of producing human-like text.
NLU: Natural Language Understanding – AI's ability to comprehend the meaning of text or speech.

Overfitting: A modeling error that occurs when a machine learning model performs well on training data but poorly on unseen data.
OCR: Optical Character Recognition – Technology that converts images of text into machine-readable data.

RL: Reinforcement Learning – A type of machine learning where agents learn by interacting with an environment to maximize rewards.
RNN: Recurrent Neural Network – A neural network designed for sequential data like time series or text.

Supervised Learning: A type of machine learning where the model is trained on labeled data.
SGD: Stochastic Gradient Descent – An optimization algorithm used in training machine learning models.
SVM: Support Vector Machine – A supervised learning algorithm used for classification and regression.

Training Data: The dataset used to train a machine learning model.
Transfer Learning: A technique where a pre-trained model is adapted to a new task by reusing its learned knowledge.
Turing TestA test proposed by Alan Turing to determine if a machine exhibits human-like intelligence.
TF-IDF: Term Frequency-Inverse Document Frequency – A statistical measure used in text analysis to determine the importance of a word in a document.
TPU: Tensor Processing Unit – A hardware accelerator for machine learning tasks developed by Google.

Unsupervised Learning: A type of machine learning where the model identifies patterns and relationships in unlabeled data.
UnderfittingA modeling error where the model is too simple to capture the underlying patterns in the data.

VAE: Variational Autoencoder – A type of generative model used for tasks like image generation and data compression.

ZSL: Zero-Shot Learning – A paradigm where an AI model handles tasks it wasn't explicitly trained on.