Exploiting the stimuli encoding scheme of evolving Spiking Neural Networks for stream learning

Lobo, Jesús L.; Oregi, Izaskun; Bifet, Albert; Ser, Javier Del

doi:10.1016/j.neunet.2019.11.021

Cited by 8 publications

(7 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Otherwise, order nr is set to ord, ord is incremented and r is incremented. The computational complexity of Algorithm 1 is linear in the number of input neurons N I size , similarly to the encoding algorithms presented in [5] or [13].…”

Section: Ensure Precalculatedmentioning

confidence: 99%

“…neurons of an eSNN are redistributed to encode the values of each bin of the histogram according to the cardinality of values in bins. As we present in the experiments, the offered encoding method provides much better classification accuracy than the other two encoding methods offered in the literature: a method that directly calculates the firing order of input neurons proposed in [5] and Gaussian Receptive Fields (GRFs) [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study of Short Text Classification with Spiking Neural Networks

Maciąg¹,

Sitek²,

Skonieczny³

et al. 2022

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Short text classification is an important task widely used in many applications. However, few works investigated applying Spiking Neural Networks (SNNs) for text classification. To the best of our knowledge, there were no attempts to apply SNNs as classifiers of short texts. In this paper, we offer a comparative study of short text classification using SNNs. To this end, we selected and evaluated three popular implementations of SNNs: evolving Spiking Neural Networks (eSNN), the NeuCube implementation of SNNs, as well as the SNNTorch implementation that is available as the Python language package. In order to test the selected classifiers, we selected and preprocessed three publicly available datasets: 20-newsgroup dataset as well as imbalanced and balanced PubMed datasets of medical publications. The preprocessed 20-newsgroup dataset consists of first 100 words of each text, while for the classification of PubMed datasets we use only a title of each publication. As a text representation of documents, we applied the TF-IDF encoding. In this work, we also offered a new encoding method for eSNN networks, that can effectively encode values of input features having non-uniform distributions. The designed method works especially effectively with the TF-IDF encoding. The results of our study suggest that SNN networks may provide the classification quality is some cases matching or outperforming other types of classifiers.

show abstract

Section: Ensure Precalculatedmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Short Text Classification with Spiking Neural Networks

Maciąg¹,

Sitek²,

Skonieczny³

et al. 2022

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

show abstract

“…In 2020, Lobo et al (2020) have suggested the predictive potential of this encoding model and concentrated on how it was applicable as a computationally lightweight, model-agnostic pre-processing phase for learning the data stream. The main intuition of the circumstances under which the above-specified population encoding approaches produced efficient predictive gains in the classification of the data stream when pre-processing was not performed.…”

Section: Optimized Weight Updated Metalearningmentioning

confidence: 99%

“…It also suffers from the problem of measure of similarity. Evolving spiking NN (Lobo et al, 2020) modifies the closeness relationship among the data samples in the feature space that is being encoded and it also provides significant enhancements in the stream learner's predictive performance. Yet, from the detected drift, it cannot recover quickly and the encoded feature spaces cannot be adapted by the GRF.…”

Section: Ijwis 176mentioning

confidence: 99%

Enhanced Data Stream Classification by Optimized Weight Updated Meta-learning: Continuous learning-based on Concept-Drift

Singh

Khaiyum

2021

IJWIS

View full text Add to dashboard Cite

Purpose The aim of continuous learning is to obtain and fine-tune information gradually without removing the already existing information. Many conventional approaches in streaming data classification assume that all arrived new data is completely labeled. To regularize Neural Networks (NNs) by merging side information like user-provided labels or pair-wise constraints, incremental semi-supervised learning models need to be introduced. However, they are hard to implement, specifically in non-stationary environments because of the efficiency and sensitivity of such algorithms to parameters. The periodic update and maintenance of the decision method is the significant challenge in incremental algorithms whenever the new data arrives. Design/methodology/approach Hence, this paper plans to develop the meta-learning model for handling continuous or streaming data. Initially, the data pertain to continuous behavior is gathered from diverse benchmark source. Further, the classification of the data is performed by the Recurrent Neural Network (RNN), in which testing weight is adjusted or optimized by the new meta-heuristic algorithm. Here, the weight is updated for reducing the error difference between the target and the measured data when new data is given for testing. The optimized weight updated testing is performed by evaluating the concept-drift and classification accuracy. The new continuous learning by RNN is accomplished by the improved Opposition-based Novel Updating Spotted Hyena Optimization (ONU-SHO). Finally, the experiments with different datasets show that the proposed learning is improved over the conventional models. Findings From the analysis, the accuracy of the ONU-SHO based RNN (ONU-SHO-RNN) was 10.1% advanced than Decision Tree (DT), 7.6% advanced than Naive Bayes (NB), 7.4% advanced than k-nearest neighbors (KNN), 2.5% advanced than Support Vector Machine (SVM) 9.3% advanced than NN, and 10.6% advanced than RNN. Hence, it is confirmed that the ONU-SHO algorithm is performing well for acquiring the best data stream classification. Originality/value This paper introduces a novel meta-learning model using Opposition-based Novel Updating Spotted Hyena Optimization (ONU-SHO)-based Recurrent Neural Network (RNN) for handling continuous or streaming data. This is the first work utilizes a novel meta-learning model using Opposition-based Novel Updating Spotted Hyena Optimization (ONU-SHO)-based Recurrent Neural Network (RNN) for handling continuous or streaming data.

show abstract

“…If the data from the grassroots can be effectively used, the valuable information hidden in the data can be mined, and the value of the data can be improved, which will provide decision-makers with a better factual basis and basis, thereby changing management methods and formulating better management and formulation to improve the quality and level of running schools [18,19]. Facing the massive data of higher education institutions, data mining technology is an intelligent information processing technology that can effectively discover knowledge from the massive data and can discover important information that people have previously ignored from the huge data information.…”

Section: Introductionmentioning

confidence: 99%

Research on Mining of Applied Mathematics Educational Resources Based on Edge Computing and Data Stream Classification

Zhou²

2021

Mobile Information Systems

View full text Add to dashboard Cite

Facing the massive data of higher education institutions, data mining technology is an intelligent information processing technology that can effectively discover knowledge from the massive data and can discover important information that people have previously ignored from the huge data information. This article is dedicated to the development of applied mathematics education resource mining technology based on edge computing and data stream classification. First of all, this article establishes a resource system architecture suitable for existing applied mathematics education through edge computing technology, which can effectively improve the efficiency of data mining. Secondly, the data stream classification algorithm is used for information extraction and classification integration of massive applied mathematical education data. This method provides potential and valuable information for decision-makers and education practitioners. Finally, the simulation and performance test of the system verify that it has the functions of mathematical information mining and data processing. This system will provide strong support for applied mathematics education reform.

show abstract

Exploiting the stimuli encoding scheme of evolving Spiking Neural Networks for stream learning

Cited by 8 publications

References 46 publications

A Comparative Study of Short Text Classification with Spiking Neural Networks

A Comparative Study of Short Text Classification with Spiking Neural Networks

Enhanced Data Stream Classification by Optimized Weight Updated Meta-learning: Continuous learning-based on Concept-Drift

Research on Mining of Applied Mathematics Educational Resources Based on Edge Computing and Data Stream Classification

Contact Info

Product

Resources

About