Resistive random access memory (RRAM) is an emerging non-volatile memory technology that can be used in neuromorphic computing hardware to exceed the limitations of traditional von Neumann architectures by merging processing and memory units. Two-dimensional (2D) materials with non-volatile switching behavior can be used as the switching layer of RRAMs, exhibiting superior behavior compared to conventional oxide-based devices. In this study, we investigate the electrical performance of 2D hexagonal boron nitride (h-BN) memristors towards their implementation in spiking neural networks (SNN). Based on experimental behavior of the h-BN memristors as artificial synapses, we simulate the implementation of unsupervised learning in SNN for image classification on the Modified National Institute of Standards and Technology dataset. Additionally, we propose a simple spike-timing-dependent-plasticity (STDP)-based dropout technique to enhance the recognition rate in h-BN memristor-based SNN. Our results demonstrate the viability of using 2D-material-based memristors as artificial synapses to perform unsupervised learning in SNN using hardware-friendly methods for online learning.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1088/1361-6528/acebf5 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Multimodal cross-scale context clusters for classification of mental disorders using functional and structural MRI.
Neural Netw
January 2025
The Key Laboratory for Computer Systems of State Ethnic Affairs Commission, Southwest Minzu University, Chengdu, Sichuan 610225, China. Electronic address:
The brain is a complex system with multiple scales and hierarchies, making it challenging to identify abnormalities in individuals with mental disorders. The dynamic segregation and integration of activities across brain regions enable flexible switching between local and global information processing modes. Modeling these scale dynamics within and between brain regions can uncover hidden correlates of brain structure and function in mental disorders.
View Article and Find Full Text PDFEHM: Exploring dynamic alignment and hierarchical clustering in unsupervised domain adaptation via high-order moment-guided contrastive learning.
Neural Netw
January 2025
College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, 310027, China. Electronic address:
Unsupervised domain adaptation (UDA) aims to annotate unlabeled target domain samples using transferable knowledge learned from the labeled source domain. Optimal transport (OT) is a widely adopted probability metric in transfer learning for quantifying domain discrepancy. However, many existing OT-based UDA methods usually employ an entropic regularization term to solve the OT optimization problem, inevitably resulting in a biased estimation of domain discrepancy.
View Article and Find Full Text PDFExploring the co-occurrence of microplastics, DOM and DBPs inside PVC pipes undergoing chlorination by correlation analysis and unsupervised learning.
Chemosphere
January 2025
Department of Civil and Environmental Engineering, National University of Singapore, 1 Engineering Drive 2, 117576, Singapore; NUS Environmental Research Institute, National University of Singapore, 5A Engineering Drive 1, 117411, Singapore. Electronic address:
Drinking water distribution systems face a multifaceted emerging concern, including in situ microplastic (MP) generation, chemical leaching from plastic pipes, and the formation of disinfection by-products (DBPs). This study investigated the co-release of MPs and chemical leachates from polyvinyl chloride (PVC) pipes exposed to different chlorine concentrations on a lab scale, as well as the subsequent formation of DBP. Results highlighted significant evidence of PVC-derived dissolved organic matter (PVC-DOM) and microplastic (PVC-MP) leaching at higher chlorine concentrations.
View Article and Find Full Text PDFDetecting low birth weight is crucial for early identification of at-risk pregnancies which are associated with significant neonatal and maternal morbidity and mortality risks. This study presents an efficient and interpretable framework for unsupervised detection of low, very low, and extreme birth weights. While traditional approaches to managing class imbalance require labeled data, our study explores the use of unsupervised learning to detect anomalies indicative of low birth weight scenarios.
View Article and Find Full Text PDFA spiking neural network for active efficient coding.
Front Robot AI
January 2025
Life- and Neurosciences, Frankfurt Institute for Advanced Studies, Frankfurt am Main, Germany.
Biological vision systems simultaneously learn to efficiently encode their visual inputs and to control the movements of their eyes based on the visual input they sample. This autonomous joint learning of visual representations and actions has previously been modeled in the Active Efficient Coding (AEC) framework and implemented using traditional frame-based cameras. However, modern event-based cameras are inspired by the retina and offer advantages in terms of acquisition rate, dynamic range, and power consumption.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!