The traditional association theory maintains that associations between cues can change only in trials where the cue is actually presented. However, the retrospective revaluation (RR) studies the phenomenon that responses to a cue can change even when the cue is not actually presented. A hardware memristor-based neural network circuit with an RR effect is proposed in this article. The neural network circuit successfully demonstrates various phenomena of RR, including the impact of deflation and inflation of companion cue associations on target cue, higher order RR, and context dependence. The correctness of the circuit design is verified by Pspice simulation. The key feature of this design lies in its ability to learn cue associations even in training trials, where the target cues are absent. This distinctive attribute offers a fresh perspective for the creation of more intricate, brain-inspired information processing systems with enhanced integration capabilities.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TNNLS.2025.3539842 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Chemometric-assisted electrochemical sensor for simultaneous determination of neonicotinoids imidacloprid and thiamethoxam in honey samples.
Anal Methods
March 2025
Departamento de Química, Instituto para el Desarrollo Agroindustrial y de la Salud (IDAS), Facultad de Ciencias Exactas, Físico-Químicas y Naturales, Universidad Nacional de Río Cuarto, Rio Cuarto 5800, Argentina.
Neonicotinoids are systemic insecticides used in agriculture. In particular, imidacloprid (IM) and thiamethoxam (TM) have selective toxicity to insects, and they have been implicated in the steep decline of the global honeybee population, specifically in colony collapse disorder (CCD). Some scientific reports have shown that a significant amount of honey worldwide contains traces of neonicotinoids, at levels strong enough to cause damage to bees.
View Article and Find Full Text PDFA multi-objective function for deep learning-based automatic energy efficiency power allocation in multicarrier noma system using hybrid heuristic improvement.
Network
March 2025
Department of Electronics and Communication Engineering, Visvesvaraya National Institute of Technology, Nagpur, India.
Non-Orthogonal Multiple Access (NOMA) is the successive multiple-access methodologies for modern communication devices. Energy Efficiency (EE) is suggested in the NOMA system. In dynamic network conditions, the consideration of NOMA shows high computational complexity that minimizes the EE to degrade the system performance.
View Article and Find Full Text PDFHead CT Scan Motion Artifact Correction via Diffusion-Based Generative Models.
Appl Med Artif Intell (2024)
February 2025
Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital and Harvard Medical School, Boston, MA, 02114, USA.
Head motion is a major source of image artifacts in head computed tomography (CT), degrading the image quality and impacting diagnosis. Image-domain-based motion correction is practical for routine use since it doesn't rely on hard-to-obtain CT projection data. However, existing convolutional neural network (CNN)-based methods tend to over-smooth images, particularly in cases of moderate to severe 3D motion artifacts.
View Article and Find Full Text PDFKAN-EEG: towards replacing backbone-MLP for an effective seizure detection system.
R Soc Open Sci
March 2025
School of Biomedical Engineering, Faculty of Engineering, The University of Sydney, Sydney, NSW 2006, Australia.
The landscape of artificial intelligence (AI) research is witnessing a transformative shift with the emergence of the Kolmogorov-Arnold network (KAN), presenting a novel architectural paradigm aimed to redefine the structural foundations of AI models, which are based on multilayer perceptron (MLP). Through rigorous experimentation and evaluation, we introduce the KAN-electroencephalogram (EEG) model, a tailored design for efficient seizure detection. Our proposed network is tested and successfully generalized on three different datasets, one from the USA, one from Europe, and one from Oceania, recorded with different front-end hardware.
View Article and Find Full Text PDFMedical image classification by incorporating clinical variables and learned features.
R Soc Open Sci
March 2025
School of Electronics and Computer Science, University of Southampton, Southampton, UK.
Medical image classification plays an important role in medical imaging. In this work, we present a novel approach to enhance deep learning models in medical image classification by incorporating clinical variables without overwhelming the information. Unlike most existing deep neural network models that only consider single-pixel information, our method captures a more comprehensive view.
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!