Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Efficient learning by the backpropagation (BP) algorithm is required for many practical applications. The BP algorithm calculates the weight changes of artificial neural networks, and a common approach is to use a two-term algorithm consisting of a learning rate (LR) and a momentum factor (MF). The major drawbacks of the two-term BP learning algorithm are the problems of local minima and slow convergence speeds, which limit the scope for real-time applications. Recently the addition of an extra term, called a proportional factor (PF), to the two-term BP algorithm was proposed. The third increases the speed of the BP algorithm. However, the PF term also reduces the convergence of the BP algorithm, and criteria for evaluating convergence are required to facilitate the application of the three terms BP algorithm. This paper analyzes the convergence of the new three-term backpropagation algorithm. If the learning parameters of the three-term BP algorithm satisfy the conditions given in this paper, then it is guaranteed that the system is stable and will converge to a local minimum. It is proved that if at least one of the eigenvalues of matrix F (compose of the Hessian of the cost function and the system Jacobian of the error vector at each iteration) is negative, then the system becomes unstable. Also the paper shows that all the local minima of the three-term BP algorithm cost function are stable. The relationship between the learning parameters are established in this paper such that the stability conditions are met.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.neunet.2005.04.007 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
High-resolution time-series transcriptomic and metabolomic profiling reveals the regulatory mechanism underlying salt tolerance in maize.
Genome Biol
September 2025
National Key Laboratory of Crop Genetic Improvement, Huazhong Agricultural University, Wuhan, 430070, China.
Background: Soil salinization represents a critical global challenge to agricultural productivity, profoundly impacting crop yields and threatening food security. Plant salt-responsive is complex and dynamic, making it challenging to fully elucidate salt tolerance mechanism and leading to gaps in our understanding of how plants adapt to and mitigate salt stress.
Results: Here, we conduct high-resolution time-series transcriptomic and metabolomic profiling of the extremely salt-tolerant maize inbred line, HLZY, and the salt-sensitive elite line, JI853.
Evaluation of deep learning-based segmentation models for carotid artery calcification detection in panoramic radiographs.
Oral Radiol
September 2025
Department of Oral and Maxillofacial Radiology, Eskisehir Osmangazi University, Meşelik Campus, Büyükdere Neighborhood, Prof. Dr. Nabi Avcı Boulevard No:4, Odunpazarı, Eskişehir, 26040, Turkey.
Objectives: The primary objective of this study is to evaluate the effectiveness of artificial intelligence-assisted segmentation methods in detecting carotid artery calcification (CAC) in panoramic radiographs and to compare the performance of different YOLO models: YOLOv5x-seg, YOLOv8x-seg, and YOLOv11x-seg. Additionally, the study aims to investigate the association between patient gender and the presence of CAC, as part of a broader epidemiological analysis.
Methods: In this study, 30,883 panoramic radiographs were scanned.
Deep-Learning System for Automatic Measurement of the Femorotibial Rotational Angle on Lower-Extremity Computed Tomography.
J Imaging Inform Med
September 2025
Department of Biomedical Engineering, Gachon University, Seongnam-Si 13120, Gyeonggi-Do, Republic of Korea.
To develop and validate a deep-learning-based algorithm for automatic identification of anatomical landmarks and calculating femoral and tibial version angles (FTT angles) on lower-extremity CT scans. In this IRB-approved, retrospective study, lower-extremity CT scans from 270 adult patients (median age, 69 years; female to male ratio, 235:35) were analyzed. CT data were preprocessed using contrast-limited adaptive histogram equalization and RGB superposition to enhance tissue boundary distinction.
View Article and Find Full Text PDFMulti-class machine learning-based classification of SCID-related genetic variants.
Immunol Res
September 2025
Department of Immunology and Allergy, Faculty of Medicine, Necmettin Erbakan University, Konya, Türkiye.
Background: Variants of uncertain significance (VUS) represent a major diagnostic challenge in the interpretation of genetic testing results, particularly in the context of inborn errors of immunity such as severe combined immunodeficiency (SCID). The inconsistency among computational prediction tools often necessitates expensive and time-consuming wet-lab analyses.
Objective: This study aimed to develop disease-specific, multi-class machine learning models using in silico scores to classify SCID-associated genetic variants and improve the interpretation of VUS.
Algorithm to detect ISUP ≥ 2 prostate cancer using canine detection.
World J Urol
September 2025
Bichat Claude Bernard Hospital, Public Assistance of Paris Hospitals, Paris, France.
Purpose: Screening and diagnosing ISUP ≥ 2 prostate cancer is challenging. This study aimed to determine whether canine detection could be beneficial addition to the ISUP ≥ 2 prostate cancer diagnostic protocol by creating a decision-making algorithm for men with suspected prostate cancer.
Methods: We conducted a prospective study at two urology institutions and a French veterinary school, including men with a suspicion of prostate cancer from November to April 2023, which were divided into two groups according to their prostate biopsy results.