AI Glossary

AI Glossary

Term Definition Colab Link Tags
Artificial Intelligence (AI) The simulation of human intelligence processes by machines, especially computer systems. Link to Colab (TBD)
General
Machine Learning (ML) A subset of AI that enables systems to learn from data and improve from experience without being explicitly programmed. Link to Colab (TBD)
GeneralCore
Deep Learning (DL) A subset of ML based on artificial neural networks with multiple layers (deep neural networks). Link to Colab (TBD)
MLNeural Networks
Neural Network A series of algorithms that endeavor to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates. Link to Colab (TBD)
DLCore
Supervised Learning A type of ML where the model is trained on labeled data. Link to Colab (TBD)
MLTraining
Unsupervised Learning A type of ML where the model is trained on unlabeled data and must find patterns on its own. Link to Colab (TBD)
MLTraining
Reinforcement Learning (RL) A type of ML where an agent learns to make decisions by performing actions and receiving rewards or penalties. Link to Colab (TBD)
MLTraining
Natural Language Processing (NLP) A field of AI focused on the interaction between computers and humans through natural language. Link to Colab (TBD)
AILanguage
Computer Vision (CV) A field of AI that enables computers to derive meaningful information from digital images, videos and other visual inputs. Link to Colab (TBD)
AIVision
Large Language Model (LLM) A deep learning algorithm that can recognize, summarize, translate, predict and generate text and other content based on knowledge gained from massive datasets. Link to Colab (TBD)
NLPGenerative AI
Generative AI A type of AI technology that can produce various types of content, including text, imagery, audio and synthetic data. Link to Colab (TBD)
AICreation
Transformer A deep learning model that adopts the mechanism of self-attention, differentially weighting the significance of each part of the input data. Link to Colab (TBD)
DLNLP
Overfitting A modeling error that occurs when a function is too closely fit to a limited set of data points, performing well on training data but properly on new data. Link to Colab (TBD)
MLError
Underfitting A modeling error that occurs when a model cannot adequately capture the underlying structure of the data. Link to Colab (TBD)
MLError
Bias The simplifying assumptions made by a model to make the target function easier to learn. High bias can cause underfitting. Link to Colab (TBD)
MLError
Variance The amount that the estimate of the target function will change if different training data was used. High variance can cause overfitting. Link to Colab (TBD)
MLError
Activation Function A function that defines the output of a node given an input or set of inputs, introducing non-linearity to the network. Link to Colab (TBD)
DLMath
Backpropagation An algorithm used for supervised learning of artificial neural networks using gradient descent. Link to Colab (TBD)
DLTraining
Epoch One complete pass of the training dataset through the algorithm. Link to Colab (TBD)
MLTraining
Loss Function A method of evaluating how well your algorithm models your dataset. Link to Colab (TBD)
MLMath