An optoelectronic neural network is presented that is designed to solve the assignment problem--or any similar optimization task given minimal adjustment--in both crossbar and banyan packet switches. We examine the design decisions made at the hardware, software, and algorithmic levels and indicate the associated effect on the system as a whole. Clearly detailed experimental results show the system's robustness and performance due to the particular optoelectronic-algorithm combination used. The integration and packaging of such a system are also briefly discussed.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1364/ao.43.000866 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave Radar.
Sensors (Basel)
January 2025
School of Information and Communication Engineering, Beijing Information Science and Technology University, Beijing 100101, China.
Human activity recognition by radar sensors plays an important role in healthcare and smart homes. However, labeling a large number of radar datasets is difficult and time-consuming, and it is difficult for models trained on insufficient labeled data to obtain exact classification results. In this paper, we propose a multiscale residual weighted classification network with large-scale, medium-scale, and small-scale residual networks.
View Article and Find Full Text PDFGFA-Net: Geometry-Focused Attention Network for Six Degrees of Freedom Object Pose Estimation.
Sensors (Basel)
December 2024
Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Chongqing University, Chongqing 400044, China.
Six degrees of freedom (6-DoF) object pose estimation is essential for robotic grasping and autonomous driving. While estimating pose from a single RGB image is highly desirable for real-world applications, it presents significant challenges. Many approaches incorporate supplementary information, such as depth data, to derive valuable geometric characteristics.
View Article and Find Full Text PDFVariable-Parameter Impedance Control of Manipulator Based on RBFNN and Gradient Descent.
Sensors (Basel)
December 2024
Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an 710119, China.
During the interaction process of a manipulator executing a grasping task, to ensure no damage to the object, accurate force and position control of the manipulator's end-effector must be concurrently implemented. To address the computationally intensive nature of current hybrid force/position control methods, a variable-parameter impedance control method for manipulators, utilizing a gradient descent method and Radial Basis Function Neural Network (RBFNN), is proposed. This method employs a position-based impedance control structure that integrates iterative learning control principles with a gradient descent method to dynamically adjust impedance parameters.
View Article and Find Full Text PDFA hybrid explainable model based on advanced machine learning and deep learning models for classifying brain tumors using MRI images.
Sci Rep
January 2025
Institute of Optoelectronics, Military University of Technology, Gen. S. Kaliskiego 2, Warsaw, 00-908, Poland.
Brain tumors present a significant global health challenge, and their early detection and accurate classification are crucial for effective treatment strategies. This study presents a novel approach combining a lightweight parallel depthwise separable convolutional neural network (PDSCNN) and a hybrid ridge regression extreme learning machine (RRELM) for accurately classifying four types of brain tumors (glioma, meningioma, no tumor, and pituitary) based on MRI images. The proposed approach enhances the visibility and clarity of tumor features in MRI images by employing contrast-limited adaptive histogram equalization (CLAHE).
View Article and Find Full Text PDFHarnessing spatiotemporal transformation in magnetic domains for nonvolatile physical reservoir computing.
Sci Adv
January 2025
Institute of Materials Research and Engineering (IMRE), Agency for Science Technology and Research (A*STAR), 2 Fusionopolis Way, #08-03 Innovis, Singapore 138634, Republic of Singapore.
Combining physics with computational models is increasingly recognized for enhancing the performance and energy efficiency in neural networks. Physical reservoir computing uses material dynamics of physical substrates for temporal data processing. Despite the ease of training, building an efficient reservoir remains challenging.
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!