Abstract
This paper presents and discusses an approach of user modeling. A set of neural networks is utilized to store, maintain and infer users' task-related characteristics. Such networks function as associative memories that can capture the causal relationships among users' characteristics for the system adaptation. It is suggested that this approach can be expected to overcome some inherent problems of the conventional stereotyping approaches in terms of pattern recognition and classification. It can also avoid the complexity of truth maintenance in default reasoning that is required in previously known stereotyping approaches.
| Original language | English |
|---|---|
| Pages (from-to) | 471-476 |
| Number of pages | 6 |
| Journal | Advances in Human Factors/Ergonomics |
| Volume | 20 |
| Issue number | B |
| DOIs | |
| State | Published - 1 Jan 1995 |
Fingerprint
Cite this
}
Associative user modeling : A neural network approach. / Chen, Qiyang; Norcio, A. F.
In: Advances in Human Factors/Ergonomics, Vol. 20, No. B, 01.01.1995, p. 471-476.Research output: Contribution to journal › Article › Research › peer-review
TY - JOUR
T1 - Associative user modeling
T2 - A neural network approach
AU - Chen, Qiyang
AU - Norcio, A. F.
PY - 1995/1/1
Y1 - 1995/1/1
N2 - This paper presents and discusses an approach of user modeling. A set of neural networks is utilized to store, maintain and infer users' task-related characteristics. Such networks function as associative memories that can capture the causal relationships among users' characteristics for the system adaptation. It is suggested that this approach can be expected to overcome some inherent problems of the conventional stereotyping approaches in terms of pattern recognition and classification. It can also avoid the complexity of truth maintenance in default reasoning that is required in previously known stereotyping approaches.
AB - This paper presents and discusses an approach of user modeling. A set of neural networks is utilized to store, maintain and infer users' task-related characteristics. Such networks function as associative memories that can capture the causal relationships among users' characteristics for the system adaptation. It is suggested that this approach can be expected to overcome some inherent problems of the conventional stereotyping approaches in terms of pattern recognition and classification. It can also avoid the complexity of truth maintenance in default reasoning that is required in previously known stereotyping approaches.
UR - http://www.scopus.com/inward/record.url?scp=77957023615&partnerID=8YFLogxK
U2 - 10.1016/S0921-2647(06)80261-3
DO - 10.1016/S0921-2647(06)80261-3
M3 - Article
VL - 20
SP - 471
EP - 476
JO - Advances in Human Factors/Ergonomics
JF - Advances in Human Factors/Ergonomics
SN - 0921-2647
IS - B
ER -