A Caltech Library Service

Monotonic Networks

Sill, Joseph (1998) Monotonic Networks. In: Advances in Neural Information Processing Systems 10 (NIPS 1997). Advances in Neural Information Processing Systems. No.10. MIT Press , Cambridge, MA, pp. 661-667. ISBN 0-262-10076-2.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


Monotonicity is a constraint which arises in many application domains. We present a machine learning model, the monotonic network, for which monotonicity can be enforced exactly, i.e., by virtue of functional form . A straightforward method for implementing and training a monotonic network is described. Monotonic networks are proven to be universal approximators of continuous, differentiable monotonic functions. We apply monotonic networks to a real-world task in corporate bond rating prediction and compare them to other approaches.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Additional Information:© 1998 Massachusetts Institute of Technology. The author is very grateful to Yaser Abu-Mostafa for considerable guidance. I also thank John Moody for supplying the data. Amir Atiya, Eric Bax, Zehra Cataltepe, Malik Magdon-Ismail, Alexander Nicholson, and Xubo Song supplied many useful comments.
Series Name:Advances in Neural Information Processing Systems
Issue or Number:10
Record Number:CaltechAUTHORS:20160223-163030288
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:64702
Deposited On:24 Feb 2016 18:32
Last Modified:03 Oct 2019 09:40

Repository Staff Only: item control page