Dataset Information

Run-off election-based decision method for the training and inference process in an artificial neural network.

ABSTRACT: Generally, the decision rule for classifying unstructured data in an artificial neural network system depends on the sequence results of an activation function determined by vector-matrix multiplication between the input bias signal and the analog synaptic weight quantity of each node in a matrix array. Although a sequence-based decision rule can efficiently extract a common feature in a large data set in a short time, it can occasionally fail to classify similar species because it does not intrinsically consider other quantitative configurations of the activation function that affect the synaptic weight update. In this work, we implemented a simple run-off election-based decision rule via an additional filter evaluation to mitigate the confusion from proximity of output activation functions, enabling the improved training and inference performance of artificial neural network system. Using the filter evaluation selected via the difference among common features of classified images, the recognition accuracy achieved for three types of shoe image data sets reached ~?82.03%, outperforming the maximum accuracy of ~?79.23% obtained via the sequence-based decision rule in a fully connected single layer network. This training algorithm with an independent filter can precisely supply the output class in the decision step of the fully connected network.

SUBMITTER: Jang J

PROVIDER: S-EPMC7806707 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Run-off election-based decision method for the training and inference process in an artificial neural network.

Jang Jingon J Jang Seonghoon S Choi Sanghyeon S Wang Gunuk G

Scientific reports 20210113 1

Generally, the decision rule for classifying unstructured data in an artificial neural network system depends on the sequence results of an activation function determined by vector-matrix multiplication between the input bias signal and the analog synaptic weight quantity of each node in a matrix array. Although a sequence-based decision rule can efficiently extract a common feature in a large data set in a short time, it can occasionally fail to classify similar species because it does not intr ...[more]

PMID: 33441631

Similar Datasets

Project description:This study aims to enhance the post-training evaluation of the annual performance agreement (APA) training organized by the Bangladesh Public Administration Training Centre (BPATC), the apex training institute for civil servants. Utilizing fuzzy-set qualitative comparative analysis (fsQCA) and artificial neural network (ANN) techniques within Kirkpatrick's four-stage model framework, data were collected from a self-administered questionnaire survey of 71 in-service civil servants who participated in the APA training program. This study employs an asymmetric, non-linear model analyzed through a configurational approach and ANN to explore interrelationships among the four Kirkpatrick levels namely, reaction, learning, behavior, and results. Findings indicate that trainees were satisfied across all levels, identifying a non-linear relationship among these levels in post-training evaluation process. The research highlights that "learning skills" are most significant in the APA post-training evaluation, followed by behavior, results, and reaction. Theoretically, this research advances Kirkpatrick's model and adds to the literature on public service post-training evaluation. Practically, it recommends prioritizing strategies that address cognitive barriers to enhance training effectiveness. This study's innovative approach lies in its concurrent use of fsQCA and ANN methods to analyze the success or failure of APA-related trainees, offering alternative pathways to desired outcomes and contrasting traditional quantitative methods that provide a single solution. The findings have practical implications for public service training institutions and bureaucratic policymakers involved in capacity development, guiding the creation of more effective in-service training courses for public officials. The methodology and analysis can be applied in other contexts, allowing bureaucratic policymakers to replicate these findings in their learning institutes to identify unique configurations that lead to successful or unsuccessful training outcomes, adopt effective strategies, and avoid detrimental ones.

Project description:Convolutional neural networks (CNNs), which automatically learn features from raw data to approximate functions, are being increasingly applied to the end-to-end analysis of electroencephalographic (EEG) signals, especially for decoding brain states in brain-computer interfaces (BCIs). Nevertheless, CNNs introduce a large number of trainable parameters, may require long training times, and lack in interpretability of learned features. The aim of this study is to propose a CNN design for P300 decoding with emphasis on its lightweight design while guaranteeing high performance, on the effects of different training strategies, and on the use of post-hoc techniques to explain network decisions. The proposed design, named MS-EEGNet, learned temporal features in two different timescales (i.e., multi-scale, MS) in an efficient and optimized (in terms of trainable parameters) way, and was validated on three P300 datasets. The CNN was trained using different strategies (within-participant and within-session, within-participant and cross-session, leave-one-subject-out, transfer learning) and was compared with several state-of-the-art (SOA) algorithms. Furthermore, variants of the baseline MS-EEGNet were analyzed to evaluate the impact of different hyper-parameters on performance. Lastly, saliency maps were used to derive representations of the relevant spatio-temporal features that drove CNN decisions. MS-EEGNet was the lightest CNN compared with the tested SOA CNNs, despite its multiple timescales, and significantly outperformed the SOA algorithms. Post-hoc hyper-parameter analysis confirmed the benefits of the innovative aspects of MS-EEGNet. Furthermore, MS-EEGNet did benefit from transfer learning, especially using a low number of training examples, suggesting that the proposed approach could be used in BCIs to accurately decode the P300 event while reducing calibration times. Representations derived from the saliency maps matched the P300 spatio-temporal distribution, further validating the proposed decoding approach. This study, by specifically addressing the aspects of lightweight design, transfer learning, and interpretability, can contribute to advance the development of deep learning algorithms for P300-based BCIs.

Dataset Information

Run-off election-based decision method for the training and inference process in an artificial neural network.

Publications

Run-off election-based decision method for the training and inference process in an artificial neural network.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets