This study introduces an artificial neural network (ANN) for image classification task, inspired by the aversive olfactory learning neural circuit in Caenorhabditis elegans (C. elegans). Although artificial neural networks (ANNs) have demonstrated remarkable performance in various tasks, they still encounter challenges including excessive parameterization, high training costs and limited generalization capabilities, etc. C. elegans, boasting a simple nervous system consisting of merely 302 neurons, is capable of exhibiting complex behaviors such as aversive olfactory learning. This research pinpoints key neural circuit related to aversive olfactory learning in C. elegans by means of behavioral experiment and high-throughput RNA sequencing, and then translates it into an architecture of ANN for image classification. Furthermore, other ANNs for image classification with different architectures are constructed for comparative performance analysis to underscore the advantages of the bio-inspired designed architecture. The results show that the ANN inspired by the aversive olfactory learning neural circuit in C. elegans attains higher accuracy, greater consistency and faster convergence rate in the image classification task, particularly when dealing with more complex classification challenges. This study not only demonstrates the potential of bio-inspired design in improving the capabilities of ANNs but also offers a novel perspective and methodology for future ANNs design.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1002/advs.202410637 | DOI Listing |
BMC Med
December 2024
Foodborne and Waterborne Diseases Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
Background: Helicobacter pylori infection causes gastritis, peptic ulcers, and gastric cancer. The infection is typically acquired in childhood and persists throughout life. The major impediment to successful therapy is antibiotic resistance.
View Article and Find Full Text PDFBiomed Tech (Berl)
December 2024
Department of Electrical Engineering, 577243 University of Science and Culture, Tehran, Iran.
Objectives: One of the primary causes of the women death is breast cancer. Accurate and early breast cancer diagnosis plays an essential role in its treatment. Computer Aided Diagnosis (CAD) system can be used to help doctors in the diagnosis process.
View Article and Find Full Text PDFZhonghua Wei Chang Wai Ke Za Zhi
December 2024
Chronic constipation is a common functional bowel disease, and its diagnosis is based on history and physical examination. Laboratory examination is important for determining the cause, type, severity and treatment effect of chronic constipation. At present, the commonly used workup of chronic constipation includes X-ray, magnetic resonance, pelvic floor ultrasound, neuroelectrophysiology and colorectal manometry, etc.
View Article and Find Full Text PDFAnn Vasc Surg
December 2024
Department of Cardiac and Vascular Surgery, University Medical Centre Mainz, Johannes Gutenberg University, Mainz, Germany.
An aorto-oesophageal fistula (AOF) is a pathological communication between the thoracic aorta and the oesophagus. It can induce life-threatening hematemesis, which is unique among the other types of gastrointestinal haemorrhage in that the vomiting is bright red and represents an arterial bleed. Nevertheless, it is notable that over 70% of cases are associated with thoracic aortic aneurysms, particularly as a postoperative complication following open surgery, and arguably more so following endovascular repair.
View Article and Find Full Text PDFRev Esp Med Nucl Imagen Mol (Engl Ed)
December 2024
Department of Nuclear Medicine, Jinling Hospital, Medical school of NanjingUniversity, Nanjing, Jiangsu Province, 210002, China.
Objective: The aim of this study is to analyze the correlation between [18F]-FDG PET/CT (positron emission tomography/computed tomography) findings and pathological subtypes of lung adenocarcinoma with ground-glass opacity (GGO).
Materials And Methods: 88 patients were included in this study, which underwent [18F]-FDG PET/CT and were finally diagnosed with lung adenocarcinoma. A total of 90 GGO lesions were analyzed.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!