eCite Digital Repository

Protocols and structures for inference: a RESTful API for machine learning


Montgomery, J and Reid, MD and Drake, B, Protocols and structures for inference: a RESTful API for machine learning, Proceedings of Machine Learning Research (PMLR) - Volume 50: 2nd Conference on Predictive APIs and Apps (PAPIs '15), 6-7 August 2015, Sydney, Australia, pp. 29-42. ISSN 1532-4435 (2016) [Refereed Conference Paper]

Restricted - Request a copy

Copyright Statement

Copyright 2016 The authors

Official URL:


Diversity in machine learning APIs (in both software toolkits and web services), works against realising machine learning’s full potential, making it difficult to draw on individual algorithms from different products or to compose multiple algorithms to solve complex tasks. This paper introduces the Protocols and Structures for Inference (PSI) service architecture and specification, which presents inferential entities - relations, attributes, learners and predictors - as RESTful web resources that are accessible via a common but flexible and extensible interface. Resources describe the data they ingest or emit using a variant of the JSON schema language, and the API has mechanisms to support non-JSON data and future extension of service features.

Item Details

Item Type:Refereed Conference Paper
Keywords:machine learning, REST, RESTful, web service, predictive API
Research Division:Information and Computing Sciences
Research Group:Distributed computing and systems software
Research Field:Service oriented computing
Objective Division:Information and Communication Services
Objective Group:Information systems, technologies and services
Objective Field:Information systems, technologies and services not elsewhere classified
UTAS Author:Montgomery, J (Dr James Montgomery)
ID Code:101369
Year Published:2016
Deposited By:Information and Communication Technology
Deposited On:2015-06-19
Last Modified:2020-04-27

Repository Staff Only: item control page