Padding
Adding extra pixels or values around data, particularly images, to preserve dimensions during convolution operations.
Common AI terms beginning with P, defined for advertising professionals.
Find the Flux+Form AI glossary & dictionary to help you make sense of common AI terms. Below you can find an AI Glossary & Dictionary for “P”.
Adding extra pixels or values around data, particularly images, to preserve dimensions during convolution operations.
A variable internal to a model whose value is learned during training.
The derivative of a multivariable function with respect to one variable while holding others constant; used in gradient computation.
The ability of an algorithm to detect patterns and regularities in data.
A simple type of neural network that makes binary classifications based on a weighted sum of inputs.
A measure such as accuracy, AUC or ROAS used to evaluate how well a model or campaign performs.
Customizing content, products or experiences to individual users using AI‑driven insights.
A series of data processing steps that transform raw data into features, feed it into a model and output predictions.
In reinforcement learning, a strategy that specifies the action a model should take in each state.
In convolutional networks, the operation that down‑samples feature maps by summarizing nearby values.
Adding positional information to token embeddings so that models can understand order in sequences.
Using statistical techniques and machine learning to forecast future outcomes such as purchase intent or churn.
Preparing data before modelling, including cleaning, scaling and encoding.
Initializing a model by training it on a large general dataset before fine‑tuning on a specific task.
A model that incorporates randomness and uncertainty into its predictions, providing distributions rather than point estimates.
Automated buying and selling of digital advertising inventory in real time via software platforms.
Crafting prompts to elicit desired outputs from generative models; small changes can significantly influence responses.
Predicting the likelihood of a particular customer action, such as buying a product, using historical data and machine learning.
Reducing the size of neural networks by removing unimportant weights or connections to improve efficiency.
The dictionary defines the words. The Creative Cadence Workshop builds the practice. Eight weeks of hands-on AI training built for ad agencies and in-house creative teams.
Learn about the workshop →