Predicting performance from test scores using backpropagation and counterpropagation

L. V. Fausett; W. Elwasif

Predicting performance from test scores using backpropagation and counterpropagation

L. V. Fausett, W. Elwasif

Research output: Contribution to conference › Paper › peer-review

37 Scopus citations

Abstract

Two neural networks for general mapping problems, backpropagation and counterpropagation, are trained to predict students' grades in Calculus I from placement test responses. The effect of the number of hidden units is investigated. The benefit of including topological structure on the cluster units of a counterpropagation net is illustrated. Noisy data sets are used to train the backpropagation net to improve the ability of the net to generalize.

Original language	English
Pages	3398-3402
Number of pages	5
State	Published - 1994
Externally published	Yes
Event	Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA Duration: Jun 27 1994 → Jun 29 1994

Conference

Conference	Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
City	Orlando, FL, USA
Period	06/27/94 → 06/29/94

Cite this

@conference{b9baacc4893541219a04d08ed8f5061f,

title = "Predicting performance from test scores using backpropagation and counterpropagation",

abstract = "Two neural networks for general mapping problems, backpropagation and counterpropagation, are trained to predict students' grades in Calculus I from placement test responses. The effect of the number of hidden units is investigated. The benefit of including topological structure on the cluster units of a counterpropagation net is illustrated. Noisy data sets are used to train the backpropagation net to improve the ability of the net to generalize.",

author = "Fausett, \{L. V.\} and W. Elwasif",

year = "1994",

language = "English",

pages = "3398--3402",

note = "Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) ; Conference date: 27-06-1994 Through 29-06-1994",

}

TY - CONF

T1 - Predicting performance from test scores using backpropagation and counterpropagation

AU - Fausett, L. V.

AU - Elwasif, W.

PY - 1994

Y1 - 1994

N2 - Two neural networks for general mapping problems, backpropagation and counterpropagation, are trained to predict students' grades in Calculus I from placement test responses. The effect of the number of hidden units is investigated. The benefit of including topological structure on the cluster units of a counterpropagation net is illustrated. Noisy data sets are used to train the backpropagation net to improve the ability of the net to generalize.

AB - Two neural networks for general mapping problems, backpropagation and counterpropagation, are trained to predict students' grades in Calculus I from placement test responses. The effect of the number of hidden units is investigated. The benefit of including topological structure on the cluster units of a counterpropagation net is illustrated. Noisy data sets are used to train the backpropagation net to improve the ability of the net to generalize.

UR - https://www.scopus.com/pages/publications/0028752806

M3 - Paper

AN - SCOPUS:0028752806

SP - 3398

EP - 3402

T2 - Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)

Y2 - 27 June 1994 through 29 June 1994

ER -

Predicting performance from test scores using backpropagation and counterpropagation

Abstract

Conference

Other files and links

Fingerprint

Cite this