Back to the Index

Inference Data

What is inference data?

Inference data is the input feature values that are the input to a trained model that outputs a prediction.

Does this content look outdated? If you are interested in helping us maintain this, feel free to contact us.

I

I

Backfill features

Backfill training data

Backpressure for feature stores

Batch Inference Pipeline

I

CI/CD for MLOps

I

DAG Processing Model

Data Compatibility

Data Partitioning

Data Transformation

Data Type (for features)

Data Validation (for features)

Data-Centric ML

Dimensional Modeling and Feature Stores

I

Encoding (for Features)

I

Feature Engineering

Feature Freshness

Feature Function

Feature Monitoring

Feature Pipeline

Feature Platform

Feature Selection

Feature Service

I

I

Hyperparameter Tuning

I

Idempotent ML Pipelines

Inference Pipeline

I

LLMs - Large Language Models

Lagged features

I

Natural Language Processing (NLP)

I

On-Demand Features

On-Demand Transformation

Online Inference Pipeline

Online-Offline Feature Skew

Online-Offline Feature Store Consistency

I

Point-in-Time Correct Joins

Precomputed Features

I

Real-Time Machine Learning

Representation Learning

I

SQL UDF in Python

Similarity Search

Splitting Training Data

Streaming Feature Pipeline

Streaming Inference Pipeline

I

Time travel (for features)

Train (Training) Set

Training Pipeline

Training-Inference Skew

I

I

Vector Database

Versioning (of ML Artifacts)

© Hopsworks 2023. All rights reserved. Various trademarks held by their respective owners.

Terms and Conditions