Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.5
3.4
Journals
Biomimetics
Special Issues
New Insights into Bio-Inspired Neural Networks
share announcement

New Insights into Bio-Inspired Neural Networks

A special issue of Biomimetics (ISSN 2313-7673). This special issue belongs to the section "Bioinspired Sensorics, Information Processing and Control".

Deadline for manuscript submissions: closed (25 April 2024) | Viewed by 2457

Special Issue Editors

Dr. Lei Zhang

E-Mail Website
Guest Editor
Engineering & Applied Science; University of Regina; 3737 Wascana Parkway; Regina, SK S4S 0A2; Canada
Interests: Bio-inspired Neural Networks, Artificial Intelligence, Machine Learning, Spiking Neural Network, FPGA Hardware Acceleration
Prof. Dr. Hanling Zhang

E-Mail Website
Guest Editor
School of Design, Hunan University, Changsha, China
Interests: video image analysis; facial expression analysis and motion capture; human-computer interaction; user experience analysis; intelligent product design

Special Issue Information

Dear Colleagues,

This Special Issue, entitled "New Insights into Bio-Inspired Neural Networks", delves into the latest advancements in the field of bio-inspired neural networks. It explores innovative approaches and insights drawn from the intricate workings of biological nervous systems. This collection of research articles showcases cutting-edge developments in neural network architectures, learning algorithms, and computational models that mimic the brain's activity and efficiency. This Special Issue provides a platform for researchers to present novel ideas, methods, and applications, ultimately contributing to the broader understanding of neural computation and its applications in artificial intelligence, robotics, and cognitive computing. Furthermore, the Special Issue explores novel strategies for designing neural network models and implementing data encoding techniques. These efforts are directed towards addressing the significant power consumption and lengthy training durations often associated with existing AI models. The overarching goal is to achieve a balance between reducing resource demands and maintaining a satisfactory level of accuracy in these systems.

Dr. Lei Zhang
Prof. Dr. Hanling Zhang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at mdpi.longhoe.net by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Biomimetics is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • bio-inspired neural networks
  • neural network architectures
  • spiking neural networks
  • data encoding techniques
  • learning algorithms
  • training efficiency
  • power-efficient AI
  • cognitive computing
  • neuromorphic computing

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

19 pages, 4470 KiB  
Article
Deep Learning and Neural Architecture Search for Optimizing Binary Neural Network Image Super Resolution
by Yuanxin Su, Li-minn Ang, Kah Phooi Seng and Jeremy Smith
Biomimetics 2024, 9(6), 369; https://doi.org/10.3390/biomimetics9060369 - 18 Jun 2024
Viewed by 403
Abstract
The evolution of super-resolution (SR) technology has seen significant advancements through the adoption of deep learning methods. However, the deployment of such models by resource-constrained devices necessitates models that not only perform efficiently, but also conserve computational resources. Binary neural networks (BNNs) offer [...] Read more.
The evolution of super-resolution (SR) technology has seen significant advancements through the adoption of deep learning methods. However, the deployment of such models by resource-constrained devices necessitates models that not only perform efficiently, but also conserve computational resources. Binary neural networks (BNNs) offer a promising solution by minimizing the data precision to binary levels, thus reducing the computational complexity and memory requirements. However, for BNNs, an effective architecture is essential due to their inherent limitations in representing information. Designing such architectures traditionally requires extensive computational resources and time. With the advancement in neural architecture search (NAS), differentiable NAS has emerged as an attractive solution for efficiently crafting network structures. In this paper, we introduce a novel and efficient binary network search method tailored for image super-resolution tasks. We adapt the search space specifically for super resolution to ensure it is optimally suited for the requirements of such tasks. Furthermore, we incorporate Libra Parameter Binarization (Libra-PB) to maximize information retention during forward propagation. Our experimental results demonstrate that the network structures generated by our method require only a third of the parameters, compared to conventional methods, and yet deliver comparable performance. Full article
(This article belongs to the Special Issue New Insights into Bio-Inspired Neural Networks)
►▼ Show Figures

Figure 1

14 pages, 2520 KiB  
Article
Neuron Circuit Based on a Split-gate Transistor with Nonvolatile Memory for Homeostatic Functions of Biological Neurons
by Hansol Kim, Sung Yun Woo and Hyung** Kim
Biomimetics 2024, 9(6), 335; https://doi.org/10.3390/biomimetics9060335 - 31 May 2024
Viewed by 364
Abstract
To mimic the homeostatic functionality of biological neurons, a split-gate field-effect transistor (S-G FET) with a charge trap layer is proposed within a neuron circuit. By adjusting the number of charges trapped in the Si3N4 layer, the threshold voltage (V [...] Read more.
To mimic the homeostatic functionality of biological neurons, a split-gate field-effect transistor (S-G FET) with a charge trap layer is proposed within a neuron circuit. By adjusting the number of charges trapped in the Si3N4 layer, the threshold voltage (Vth) of the S-G FET changes. To prevent degradation of the gate dielectric due to program/erase pulses, the gates for read operation and Vth control were separated through the fin structure. A circuit that modulates the width and amplitude of the pulse was constructed to generate a Program/Erase pulse for the S-G FET as the output pulse of the neuron circuit. By adjusting the Vth of the neuron circuit, the firing rate can be lowered by increasing the Vth of the neuron circuit with a high firing rate. To verify the performance of the neural network based on S-G FET, a simulation of online unsupervised learning and classification in a 2-layer SNN is performed. The results show that the recognition rate was improved by 8% by increasing the threshold of the neuron circuit fired. Full article
(This article belongs to the Special Issue New Insights into Bio-Inspired Neural Networks)
►▼ Show Figures

Figure 1

16 pages, 3332 KiB  
Article
Motor Interaction Control Based on Muscle Force Model and Depth Reinforcement Strategy
by Hongyan Liu, Hanwen Zhang, Junghee Lee, Peilong Xu, Incheol Shin and Jongchul Park
Biomimetics 2024, 9(3), 150; https://doi.org/10.3390/biomimetics9030150 - 1 Mar 2024
Viewed by 1210
Abstract
The current motion interaction model has the problems of insufficient motion fidelity and lack of self-adaptation to complex environments. To address this problem, this study proposed to construct a human motion control model based on the muscle force model and stage particle swarm, [...] Read more.
The current motion interaction model has the problems of insufficient motion fidelity and lack of self-adaptation to complex environments. To address this problem, this study proposed to construct a human motion control model based on the muscle force model and stage particle swarm, and based on this, this study utilized the deep deterministic gradient strategy algorithm to construct a motion interaction control model based on the muscle force model and the deep reinforcement strategy. Empirical analysis of the human motion control model proposed in this study revealed that the joint trajectory correlation and muscle activity correlation of the model were higher than those of other comparative models, and its joint trajectory correlation was up to 0.90, and its muscle activity correlation was up to 0.84. In addition, this study validated the effectiveness of the motion interaction control model using the depth reinforcement strategy and found that in the mixed-obstacle environment, the model’s desired results were obtained by training 1.1 × 103 times, and the walking distance was 423 m, which was better than other models. In summary, the proposed motor interaction control model using the muscle force model and deep reinforcement strategy has higher motion fidelity and can realize autonomous decision making and adaptive control in the face of complex environments. It can provide a theoretical reference for improving the effect of motion control and realizing intelligent motion interaction. Full article
(This article belongs to the Special Issue New Insights into Bio-Inspired Neural Networks)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop