In this study, a binarized neural network (BNN) of silicon diode arrays achieved vector-matrix multiplication (VMM) between the binarized weights and inputs in these arrays. The diodes that operate in a positive-feedback loop in their p-n-p-n device structure possess steep switching and bistable characteristics with an extremely low subthreshold swing (below 1 mV) and a high current ratio (approximately 10). Moreover, the arrays show a self-rectifying functionality and an outstanding linearity by an R-squared value of 0.99986, which allows to compose a synaptic cell with a single diode. A 2 × 2 diode array can perform matrix multiply-accumulate operations for various binarized weight matrix cases with some input vectors, which is in high concordance with the VMM, owing to the high reliability and uniformity of the diodes. Moreover, the disturbance-free, nondestructive readout, and semi-permanent holding characteristics of the diode arrays support the feasibility of implementing the BNN.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10928169 | PMC |
| http://dx.doi.org/10.1038/s41598-024-56575-4 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
The Classification of Metastatic Spine Cancer and Spinal Compression Fractures by Using CNN and SVM Techniques.
Bioengineering (Basel)
December 2024
Department of Orthopaedic Surgery, Institute of Medical Science, Gyeongsang National University College of Medicine and Gyeongsang National University Hospital, Jinju 52727, Republic of Korea.
Metastatic spine cancer can cause pain and neurological issues, making it challenging to distinguish from spinal compression fractures using magnetic resonance imaging (MRI). To improve diagnostic accuracy, this study developed artificial intelligence (AI) models to differentiate between metastatic spine cancer and spinal compression fractures in MRI images. MRI data from Gyeongsang National University Hospital, collected from January 2019 to April 2022, were processed using Otsu's binarization and Canny edge detection algorithms.
View Article and Find Full Text PDFA novel particle size distribution correction method based on image processing and deep learning for coal quality analysis using NIRS-XRF.
Talanta
December 2024
State Key Laboratory of Quantum Optics and Quantum Optics Devices, Institute of Laser Spectroscopy, Shanxi University, Taiyuan, 030006, China; Collaborative Innovation Center of Extreme Optics, Shanxi University, Taiyuan, 030006, China.
The combined application of near-infrared spectroscopy (NIRS) and X-ray fluorescence spectroscopy (XRF) has achieved remarkable results in coal quality analysis by leveraging NIRS's sensitivity to organic compounds and XRF's reliability for inorganic composition. However, variations in particle size distribution negatively affect the diffuse reflectance of NIRS and the fluorescence signal intensities of XRF, leading to decreased accuracy and repeatability in predictions. To address this issue, this study innovatively proposes a particle size correction method that integrates image processing and deep learning.
View Article and Find Full Text PDFLow-power and lightweight spiking transformer for EEG-based auditory attention detection.
Neural Netw
December 2024
School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China.
EEG signal analysis can be used to study brain activity and the function and structure of neural networks, helping to understand neural mechanisms such as cognition, emotion, and behavior. EEG-based auditory attention detection is using EEG signals to determine an individual's level of attention to specific auditory stimuli. In this technique, researchers record and analyze a subject's electrical activity to infer whether an individual is paying attention to a specific auditory stimulus.
View Article and Find Full Text PDFAn innovative methodology for segmenting vessel like structures using artificial intelligence and image processing.
Sci Rep
December 2024
AudacIA: Center for Research, Technological Development and Innovation in Artificial Intelligence and Robotics, Universidad Simon Bolivar, Cra 53 #64 - 51, Barranquilla, Atlantico, 080002, Colombia.
Article Synopsis
- Innovation through process automation is improving performance in various fields, but recognizing details in images remains challenging due to variations and specific conditions.
- Artificial intelligence simplifies this issue by using algorithms that detect specific pixels for image segmentation, utilizing modules like Efficient Sub-Pixel Convolutional Neural Networks and U-Net for effective capillary structure identification.
- The developed model demonstrated strong performance across multiple datasets, achieving high metrics (PSNR of 37.92 and SSIM of 0.9219), and showcased its complexity in processing with varied execution times for its enhancement, segmentation, and masking modules.
Image analysis-based identification of high risk ER-positive, HER2-negative breast cancers.
Breast Cancer Res
December 2024
Department of Epidemiology, University of North Carolina, Chapel Hill, NC, USA.
Article Synopsis
- Researchers focused on breast cancer subtypes Luminal A and Luminal B, using machine learning to analyze H&E images, aiming to identify tumor characteristics linked to higher recurrence risks.
- The study involved training models on segmented images of tumors, finding that an image-based protocol effectively predicted recurrence times, comparable to traditional genomic testing methods (PAM50).
- Results indicated that while adjusting for tumor grade didn't significantly improve subtype prediction, the image analysis provided a viable alternative in identifying patients in need of genomic testing, potentially increasing testing rates among ER+/HER2-patients.
Want 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!