Multilayer Perceptron and Learning Vector Quantization: A Comparison
Session
Computer Science and Communication Engineering
Description
In this paper we will train two Neural Computing algorithms on the Habbermann Survival dataset and compare their efficacy on predicting a patient’s survival status, five years after breast cancer operation. The data generated in Habbermann’s case study can be used with effective Machine learning algorithms to generate effective prognoses for patients. This paper compares a Multi Layer Perceptron with Marquardt Levenberg Backpropagation (MLP) and Learning Vector Quantization (LVQ) in terms of accurate target predictions (survived or didn’t survive), using the three available predictors.
Keywords:
neural networks, backpropagation, vector quantization, deep learning, prediction, axillary nodes
Session Chair
Xhafer Krasniqi
Session Co-Chair
Driart Elshani
Proceedings Editor
Edmond Hajrizi
ISBN
978-9951-550-19-2
Location
Pristina, Kosovo
Start Date
26-10-2019 3:30 PM
End Date
26-10-2019 5:00 PM
DOI
10.33107/ubt-ic.2019.288
Recommended Citation
Gjergji, Nora and Patel, Sunil, "Multilayer Perceptron and Learning Vector Quantization: A Comparison" (2019). UBT International Conference. 288.
https://knowledgecenter.ubt-uni.net/conference/2019/events/288
Multilayer Perceptron and Learning Vector Quantization: A Comparison
Pristina, Kosovo
In this paper we will train two Neural Computing algorithms on the Habbermann Survival dataset and compare their efficacy on predicting a patient’s survival status, five years after breast cancer operation. The data generated in Habbermann’s case study can be used with effective Machine learning algorithms to generate effective prognoses for patients. This paper compares a Multi Layer Perceptron with Marquardt Levenberg Backpropagation (MLP) and Learning Vector Quantization (LVQ) in terms of accurate target predictions (survived or didn’t survive), using the three available predictors.