AWhat changed
Provided a computational-network abstraction and CPU/GPU toolkit for expressing neural model graphs, with forward/gradient computation and reusable model/network descriptions.
Scientific scope
Provided a computational-network abstraction and CPU/GPU toolkit for expressing neural model graphs, with forward/gradient computation and reusable model/network descriptions. The family combines the 2014 computational-network introduction with a separately authored 2016 toolkit account. Later details are not backdated. Computational graphs, automatic differentiation and existing model types are inherited; arbitrary-topology descriptions do not guarantee that cyclic programs converge or execute unchanged.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. The family combines the 2014 computational-network introduction with a separately authored 2016 toolkit account. Later details are not backdated. Computational graphs, automatic differentiation and existing model types are inherited; arbitrary-topology descriptions do not guarantee that cyclic programs converge or execute unchanged.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- An introduction to computational networks and the computational network toolkit (invited talk)
- An Introduction to Computational Networks and the Computational Network Toolkit —17February2016draft
- Microsoft Research: CNTK report index and linked revision
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction