Inference Machine Learning
noun
Definition 1: Probabilistic reasoning; the computation of posterior distributions or latent variables from observed data and a model [Machine Learning Glossary].
Example in context:“However, when using undirected PGMs with hidden variables, two sources of error typically compound in all but the simplest models (a) learning error (both computing the partition function and integrating out the hidden variables is intractable); and (b) prediction error (exact inference is also intractable).” [Lázaro-Gredilla et al. 2020]
Definition 2: Prediction or the forward pass of a trained model on new data [Machine Learning Glossary 2025].
Example in context: “Mobile devices, however, often lack the resources necessary for deep learning, leading to long inference latency and quick battery consumption.” [Liu et al. 2024]
Synonym: probabilistic reasoning (in sense 1); prediction (in sense 2)
Related terms: posterior inference, latent variable, forward pass, prediction, model serving, edge inference