Related Concept Videos
Network Function of a Circuit
Biasing of FET
In an N-channel JFET, the structure consists of N-type material forming the channel on a P-type substrate, with the...
Fast Decoupled and DC Powerflow
Neural Circuits
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Design Example: Capacitance Multiplier Circuit
The circuit illustrated in Figure 1 below incorporates two op-amps, with the first operating as a voltage follower and the second acting as an inverting amplifier.
Ampere-Maxwell's Law: Problem-Solving
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
FPGA Implementation of a Radar-Based Fall Detection System Using Binarized Convolutional Neural Networks.
FMCW Radar Sensors with Improved Range Precision by Reusing the Neural Network.
Related Experiment Video
Updated: Jun 29, 2025

Author Spotlight: Modular Neuronal Networks for Analyzing Brain Functions
Published on: June 7, 2024
Design of Network-on-Chip-Based Restricted Coulomb Energy Neural Network Accelerator on FPGA Device.
Soongyu Kang1, Seongjoo Lee2,3, Yunho Jung1,4
1School of Electronics and Information Engineering, Korea Aerospace University, Goyang 10540, Republic of Korea.
This study introduces a scalable network-on-chip (NoC)-based accelerator for restricted Coulomb energy neural networks (RCE-NNs) on edge devices. The novel design significantly improves performance for AI-powered sensor applications in the Internet of Things (IoT).
More Related Videos
10:32Design, Surface Treatment, Cellular Plating, and Culturing of Modular Neuronal Networks Composed of Functionally Inter-connected Circuits
Published on: April 15, 2015
11:18Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
Area of Science:
- Artificial Intelligence
- Computer Engineering
- Internet of Things
Background:
- Edge-based artificial intelligence (AI) computation is preferred for low-latency Internet of Things (IoT) systems.
- Restricted Coulomb Energy Neural Networks (RCE-NNs) are suitable for edge devices due to their simple learning and adaptable structure.
- Existing RCE-NN accelerators face scalability challenges with increasing neuron counts.
Purpose of the Study:
- To propose a scalable network-on-chip (NoC)-based accelerator for RCE-NNs.
- To implement and evaluate the proposed accelerator on a field-programmable gate array (FPGA).
- To address the limitations of previous RCE-NN accelerators in handling a large number of neurons.
Main Methods:
- Development of a novel RCE-NN accelerator utilizing a network-on-chip (NoC) architecture.
- Implementation of a hierarchical-star (H-star) topology for efficient neuron management.
- Design of specialized routers optimized for RCE-NN communication.
- Deployment and testing on a field-programmable gate array (FPGA) platform.
Main Results:
- The proposed NoC-based RCE-NN accelerator demonstrates improved scalability with minimal decrease in maximum operating frequency as neuron count increases.
- A 126.1% increase in maximum operating frequency was observed for the accelerator with 512 neurons compared to prior designs.
- Significant accelerations were achieved in learning time (up to 54.8%) and recognition time (up to 45.7%) for gas and sign language recognition datasets.
Conclusions:
- The NoC-based RCE-NN accelerator effectively ensures neural network scalability for edge AI applications.
- The proposed architecture provides a robust solution for high-performance on-chip learning and real-time recognition in IoT systems.
- This approach overcomes previous limitations, enabling more complex AI tasks on resource-constrained edge devices.