<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Spiking topic model &#8211; Od Informacji do Wiedzy</title>
	<atom:link href="https://profind.pl/en/tag/spiking-topic-model-en/feed/" rel="self" type="application/rss+xml" />
	<link>https://profind.pl</link>
	<description>Blog o informacjach na temat informacji i wiedzy</description>
	<lastBuildDate>Wed, 12 Feb 2025 17:02:47 +0000</lastBuildDate>
	<language>en-GB</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=7.1.4</generator>
	<item>
		<title>Leveraging spiking neural networks for topic modeling</title>
		<link>https://profind.pl/en/2025/01/13/article-leveraging-spiking-neural-networks-for-topic-modeling/</link>
					<comments>https://profind.pl/en/2025/01/13/article-leveraging-spiking-neural-networks-for-topic-modeling/#respond</comments>
		
		<dc:creator><![CDATA[Marcin]]></dc:creator>
		<pubDate>Mon, 13 Jan 2025 14:36:19 +0000</pubDate>
				<category><![CDATA[Articles]]></category>
		<category><![CDATA[Spiking neural network]]></category>
		<category><![CDATA[Spiking topic model]]></category>
		<category><![CDATA[STDP]]></category>
		<category><![CDATA[Topic modeling]]></category>
		<category><![CDATA[Unsupervised learning]]></category>
		<guid isPermaLink="false">https://profind.pl/?p=1537</guid>

					<description><![CDATA[Abstract This article investigates the application of spiking neural networks (SNNs) to the problem of topic modeling (TM): the identification of significant groups of words that represent human-understandable topics in large sets of documents. Our research is based on the hypothesis that an SNN that implements the Hebbian learning paradigm is capable of becoming specialized in the detection of [&#8230;]]]></description>
										<content:encoded><![CDATA[
<h2 class="wp-block-heading section-title u-h4 u-margin-l-top u-margin-xs-bottom">Abstract</h2>


<p style="text-align: justify;"><span style="box-sizing: border-box; margin: 0px; padding: 0px;"><span style="box-sizing: border-box; margin: 0px; padding: 0px; text-align: justify;">This article investigates the application of spiking neural networks<span style="box-sizing: border-box; margin: 0px; padding: 0px;"> (SNNs) to the problem of topic modeling (TM): the identification of significant groups of words that represent human-understandable topics in large sets of documents. Our research is based on the hypothesis that an SNN that implements the Hebbian learning paradigm is capable of becoming specialized in the detection of statistically significant word patterns in the presence of adequately tailored sequential input. To support this hypothesis, we propose a novel spiking topic model (STM) that transforms text into a sequence of spikes and uses that sequence to train single-layer SNNs. In STM, each SNN neuron represents one topic, and each of the neuron’s weights corresponds to one word. STM </span></span>synaptic connections<span style="box-sizing: border-box; margin: 0px; padding: 0px;"> are modified according to spike-timing-dependent plasticity; after training, the neurons’ strongest weights are interpreted as the words that represent topics. We compare the performance of STM with four other TM methods Latent Dirichlet Allocation (LDA), Biterm Topic Model (BTM), Embedding Topic Model (ETM) and BERTopic on three datasets: </span></span><em style="box-sizing: border-box; margin: 0px; padding: 0px;">20Newsgroups</em>, <em style="box-sizing: border-box; margin: 0px; padding: 0px;">BBC news</em>, and <em style="box-sizing: border-box; margin: 0px; padding: 0px;">AG news</em><span style="box-sizing: border-box; margin: 0px; padding: 0px;">. The results demonstrate that STM can discover high-quality topics and successfully compete with comparative classical methods. This sheds new light on the possibility of the adaptation of SNN models in unsupervised natural language processing.</span></p>

]]></content:encoded>
					
					<wfw:commentRss>https://profind.pl/en/2025/01/13/article-leveraging-spiking-neural-networks-for-topic-modeling/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
	</channel>
</rss>
