International journal of neural systems最新文献

{"title":"Progressive Disambiguation and Sycophancy Mitigation for Prompt Uncertainty in Generative AI.","authors":"Fabrizio Marozzo, Loris Belcastro","doi":"10.1142/S0129065727500067","DOIUrl":"https://doi.org/10.1142/S0129065727500067","url":null,"abstract":"<p><p>Generative AI systems increasingly support users in coding, data analysis, and creative tasks through natural-language interaction. However, user prompts are often underspecified or ambiguous, and current LLM-based assistants typically proceed with a plausible interpretation, leaving misalignments to be discovered only after the output is inspected or executed. This behavior can trigger costly trial-and-error prompt revisions and may be amplified by sycophantic tendencies that reinforce incorrect assumptions. We present a progressive disambiguation framework that resolves prompt uncertainty before producing a final answer. The framework separates intent clarification from solution synthesis by guiding users through a structured pre-generation dialogue that elicits missing constraints, compares alternative interpretations, and illustrates consequences via targeted input-output examples and representative edge cases. In addition, it performs incremental constraint consistency checks that flag implausible or conflicting user-provided assumptions and request explicit confirmation before generation. After incompatible interpretations are pruned and constraints are validated, the system generates a single, intent-aligned solution. Experiments on a diverse benchmark covering coding, data analysis, and creative writing show that our approach improves output accuracy, reduces corrective iterations and overall user effort, and achieves competitive end-to-end resolution time and higher user satisfaction compared to one-shot and reactive clarification baselines.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2750006"},"PeriodicalIF":6.4,"publicationDate":"2026-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148551775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Zero-Shot Evolutionary Architecture Search for Low-Rank Adaptation.","authors":"Pengjin Wu, Ferrante Neri, Zhenhua Feng","doi":"10.1142/S0129065726500255","DOIUrl":"10.1142/S0129065726500255","url":null,"abstract":"<p><p>Fine-tuning large-scale Transformer-based models is computationally expensive due to the enormous parameter space. Low-Rank Adaptation (LoRA) substantially reduces the number of trainable parameters while maintaining performance; however, identifying the optimal LoRA configuration - such as rank <i>r</i>, scaling factor [Formula: see text], and insertion positions - remains challenging. To address this issue, we propose a zero-shot proxy metric, termed Gradient Projection Score (GPS), which enables rapid evaluation of candidate configurations using only a few forward and backward passes. Building upon this metric, we further introduce <i>EvoLoRA</i>, a zero-shot evolutionary architecture search method that jointly optimizes three objectives: performance proxy, evaluation stability, and trainable parameter size. EvoLoRA automatically discovers effective LoRA configurations across different models and datasets. Experimental results demonstrate that GPS is strongly correlated with final model performance; moreover, on tasks such as image classification and object detection, EvoLoRA markedly reduces search and training costs while generally outperforming other fine-tuning methods and manually designed LoRA configurations.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650025"},"PeriodicalIF":6.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147489003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Lightweight Dual-Attention Neural Network for Robust and Efficient EEG Motor Imagery Decoding.","authors":"Guangying Wang, Xipeng Song, Lin Jiang, Yulin Zhang, Dezhong Yao, Jing Lu, Peng Xu, Fali Li","doi":"10.1142/S0129065726500267","DOIUrl":"10.1142/S0129065726500267","url":null,"abstract":"<p><p>Motor imagery-based brain-computer interface (MI-BCI) faces a critical challenge in achieving effective spatial-temporal feature modeling while maintaining a compact model parameterization. Herein, a lightweight model was proposed, termed as Dual-Attention-EEGNet (DA-EEGNet), which extends the EEGNet backbone by integrating a channel attention module and a depth attention module to selectively emphasize informative electrodes and temporally discriminative features. Two widely used MI benchmark datasets and three evaluation strategies, i.e. subject-dependent scenario, subject-independent scenario, and dataset-independent classification scenario, were utilized to verify the model's performance. Despite its compact design, DA-EEGNet contains merely 3.97[Formula: see text]k trainable parameters and achieves average classification accuracies of [Formula: see text] and [Formula: see text], outperforming or matching existing deep learning approaches that rely on substantially larger parameter counts. Ablation studies further confirm the complementary contributions of the channel and depth attention modules. In addition, visualization analyses, including temporal attention heatmaps and motor-area topographies, demonstrate that DA-EEGNet captures neurophysiologically meaningful spatial-temporal patterns consistent with MI-related brain activity. These results indicate that DA-EEGNet provides a favorable parameter-accuracy trade-off and serves as an efficient and interpretable baseline for MI-BCI applications.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650026"},"PeriodicalIF":6.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147489008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Motor and Cognitive Imagery Detection from MEG Signals Using Wavelet-Based Common Spatial Pattern Analysis.","authors":"Gokce Koc, Mosab A A Yousif, Mahmut Ozturk","doi":"10.1142/S012906572650022X","DOIUrl":"10.1142/S012906572650022X","url":null,"abstract":"<p><p>Brain-computer interface (BCI) technology supports the interactions of individuals with severe neuromuscular limitations with their environment. This work presents a classification approach for distinguishing motor imagery (MI) from speech-related cognitive imagery (CI) such as word generation and arithmetic subtraction, using magnetoencephalography (MEG) signals. Differentiating MI and CI/SI processes is relevant for expanding command diversity in hybrid BCI systems and for clarifying the distinct neural mechanisms underlying motor versus verbal-semantic processing. Although a large proportion of noninvasive BCI studies focus on MI, this distinction has received relatively limited attention, particularly in MEG-based approaches. Making this distinction is important for increasing command diversity in hybrid BCI systems and for improving the understanding of neural mechanisms associated with motor and verbal-semantic processing. Tasks from an open-access MEG dataset were analyzed across six binary pairs (H-F, H-W, H-S, F-W, F-S, W-S). MEG signals were processed using two frequency-separation strategies: a broad-band configuration (FSB-1: 8-14[Formula: see text]Hz and 14-30[Formula: see text]Hz) and a narrow-band configuration (FSB-2: six sub-bands between 8 and 32[Formula: see text]Hz). Time-frequency features were extracted using continuous wavelet transform (CWT), and spatial features via the common spatial pattern (CSP) method. Feature selection followed a two-stage procedure: (i) <i>t</i>-test ranking to obtain a shared feature set for all task pairs; and (ii) subject- and task-specific optimization of feature number. The initial evaluation based on the shared feature set showed that the FSB-2/CWT approach yielded better classification accuracies compared to FSB-1/CWT (H-F: 56%, H-W: 71%, H-S: 66% versus 54%, 68%, 64%). With subject- and task-adaptive optimization, additional improvements were observed. Accuracies increased to 60%, 72%, and 69% for FSB-1, and to 63%, 75%, and 71% for FSB-2, for H-F, H-W, and H-S, respectively. Overall, the findings indicate that the proposed CWT[Formula: see text]CSP framework, particularly when combined with adaptive feature optimization, offers an interpretable analysis approach that can contribute to MI-CI discrimination in MEG-based BCI systems under limited data conditions.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650022"},"PeriodicalIF":6.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147391869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Exploration and Exploitation in Tumor Treatment Through Action-Guided Deep Reinforcement Learning.","authors":"Chengrong Yu, Zhonglian Wei, Yuncheng Shen, Yingyong Yin, Zhang Yi, Ying Song, Guangjun Li, Junjie Hu","doi":"10.1142/S0129065726500206","DOIUrl":"10.1142/S0129065726500206","url":null,"abstract":"<p><p>Inverse treatment planning is pivotal in tumor treatment planning. It enables the multi-objective optimization of radiation dose delivery, ensuring precise tumor targeting while sparing surrounding healthy tissues. This process often requires frequent parameter adjustments to achieve the desired balance between objectives, making it both labor-intensive and time-consuming. Deep reinforcement learning (DRL) provides an automated, model-based planning solution, aimed at reducing reliance on human expertise and enhancing the efficiency of objective parameter optimization. However, most current approaches apply DRL to inverse planning without fully leveraging the knowledge embedded in the continuous state-action space, defined by the coupling between nonstationary planning states and continuous decision variables. This may result in insufficient exploration and exploitation, leading to inefficient optimization. This work introduces an innovative action-guided DRL (AgDRL) approach for automatic inverse planning. Our goal is to enhance exploration and exploitation by leveraging insightful guidance from reward-guided actions. The implementation of AgDRL incorporates both exploitation and exploration in the action-state space. For exploitation, high-reward actions are employed as guidance to achieve the optimal action adjustment. For exploration, low-reward actions are recommended as training resets to explore a broader range of the latent state space. Quantitative and qualitative experiments are conducted in various settings to evaluate the proposed method. The results are assessed using DRL-related metrics (e.g. reward gains) and clinical-related measurements (e.g. dose-volume histograms, DVHs). Experimental results on a real-world rectal cancer dataset empirically demonstrate that the proposed AgDRL-based approach significantly improves optimization efficiency through a high-reward strategy while enhancing exploration diversity via a low-reward strategy, consistently outperforming the MatRad treatment planning optimization platform.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650020"},"PeriodicalIF":6.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147489048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Feasibility Study of Navigating Emotional States Using Real-Time Representational Similarity Analysis fMRI Neurofeedback.","authors":"Xuelei Wang, Assunta Ciarlo, Michael Lührs, Alexander Atanasyan, David Böken, Jürgen Roßmann, Michael Schluse, Maren Jäger, Marisa Nordt, Fengyu Cong, Klaus Mathiak, David E J Linden, Rainer Goebel, David M A Mehler, Jana Zweerings","doi":"10.1142/S0129065726500188","DOIUrl":"10.1142/S0129065726500188","url":null,"abstract":"<p><p>Real-time functional magnetic resonance imaging neurofeedback (rt-fMRI-NF) is a promising noninvasive brain computer interface (BCI) technique for enhancing self-regulation of affective brain states. However, conventional univariate rt-fMRI-NF approaches struggle to discriminate distributed neural patterns underlying distinct emotions. This study implemented an rt-fMRI semantic neurofeedback (rt-fMRI-sNF) paradigm incorporating real-time representational similarity analysis (rt-RSA) to enable navigation among emotional states. Four emotion-specific base patterns were first derived from functional localizer runs and then used as target patterns during neurofeedback. Using an RSA-informed circular semantic map (CSM), participants received real-time visual feedback indicating both the similarity and intensity of their current brain activity relative to target patterns. Participants were instructed to use mental imagery to shift their brain activity toward the specific target pattern and enhance its intensity. Analyses of localizer data revealed overlapping regional activations across emotions and demonstrated that RSA reliably distinguished between emotional states. Group-level mixed-effects modeling of neurofeedback performance indicated significant within-run improvements and higher initial performance in the second run. Together, these results demonstrate the methodological feasibility of an RSA-informed rt-fMRI-NF framework for multivariate brain-state modulation and establish a foundation for future studies examining its transferability and clinical relevance.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650018"},"PeriodicalIF":6.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147464557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spiking Neural Membrane Systems with Multiplexed Neurons for Enhanced Parallel Computing.","authors":"Liping Wang, Xiyu Liu, Yuzhen Zhao","doi":"10.1142/S0129065726500139","DOIUrl":"10.1142/S0129065726500139","url":null,"abstract":"<p><p>Spiking neural membrane systems (SNP systems) are distributed parallel computing models inspired by neuronal spike mechanisms. Traditional SNP systems execute rules serially within each neuron, limiting their efficiency. This paper introduces MNSNP systems, a novel variant where neurons can distinguish spike sources and execute multiple rules in parallel at one time step. MNSNP systems maintain global distributed parallelism while integrating local parallelism, significantly enhancing information processing capabilities. Computational completeness is demonstrated, proving MNSNP systems as Turing universal devices for number generation, acceptance, and function computation. Compared to existing models, MNSNP systems require fewer neurons (only 60 for universal computation), showcasing resource efficiency. An application in smoke detection achieves an AUC value of 0.9840, demonstrating practical utility. This work advances SNP systems by introducing multiplexing, paving the way for applications in robotics, feature recognition, and real-time processing.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650013"},"PeriodicalIF":6.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146069343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Achieving Optimal Accuracy and Robustness Through Tight Excitatory-Inhibitory Balance in Shallow Spiking Recurrent Neural Network.","authors":"Shiwen Li, Junsong Wang, Syeda Shamaila Zareen","doi":"10.1142/S0129065726500176","DOIUrl":"10.1142/S0129065726500176","url":null,"abstract":"<p><p>Traditional deep neural networks exhibit high computational complexity during training and lack biological interpretability due to their reliance on backpropagation-based methods. Spiking Recurrent Neural Network (SRNN) performs well in processing spatio-temporal information by using discrete spike events. It attracts increasing attention in neural computing due to its biological plausibility and hardware implementation. To improve the performance of SRNN, we propose an excitation-inhibition balanced shallow SRNN (EI-SRNN), which is inspired by the balance of excitation and inhibition in the brain, by optimizing the input currents of reservoir neurons to achieve a tight balanced state. The proposed EI-SRNN achieves optimal accuracy while maintaining low computational complexity, debunking the conventional trade-off between accuracy and robustness. We analyze the neural encoding ability and information memory capacity of the EI-SRNN and compare the performance of the model under different degrees of excitation and inhibition. Our experiments demonstrate that EI-SRNN can have higher neural coding capacity and memory capacity under tight balanced excitatory and inhibitory balanced states, so it can achieve better accuracy while possessing stronger robustness. Furthermore, when the reservoir is dominated by excitatory influences, performance declines faster than when the reservoir is dominated by inhibitory influences.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650017"},"PeriodicalIF":6.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147273701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Epileptic Seizure Detection from EEG Signals with Long Short-Term Memory-Transformer and Self-Supervised Learning.","authors":"Tiantian Xiao, Chenxi Nie, Wenqian Feng, Hao Peng, Yongfeng Zhang, Yanna Zhao","doi":"10.1142/S0129065726500127","DOIUrl":"10.1142/S0129065726500127","url":null,"abstract":"<p><p>Electroencephalogram (EEG) plays a vital role in seizure detection, yet existing methods often fail to adequately capture the spatiotemporal characteristics of EEG signals, leading to limited performance. Moreover, most current models depend on supervised learning and thus require large amounts of labeled data. To address these issues, this paper introduces the Long Short-Term Memory-Transformer (LTformer) encoder, designed to model long-term temporal dependencies in EEG signals while retaining spatial information across electrode channels. We further propose a dual-stream self-supervised learning (SSL) strategy to pretrain the model, enabling the LTformer encoder to learn discriminative representations from extensive unlabeled EEG data. After pretext training, the encoder is transferred and fine-tuned for downstream seizure detection. The proposed method, termed Self-Supervised Attention LTformer (SALT), is evaluated on two public EEG datasets using both segment-based and event-based experimental protocols. In the segment-based evaluation, SALT achieves 98.87% sensitivity, 99.15% accuracy, and 99.41% specificity on CHB-MIT, and 98.04% sensitivity, 97.72% accuracy, and 97.62% specificity on Siena. In the event-based evaluation, SALT attains 98.57% sensitivity with a false discovery rate (FDR) of 0.26 on CHB-MIT, and 98.65% sensitivity with an FDR of 0.25 on Siena. The code is publicly available at https://github.com/peutim114/SALT.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650012"},"PeriodicalIF":6.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146115341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the Effects of Emotional Sensory Stimuli on Modulating Driver Fatigue via EEG-based Spatial-Temporal Dynamic Analysis.","authors":"Fo Hu, Qinxu Zheng, Junlong Xiong, Hongsheng Chang, Zukang Qiao","doi":"10.1142/S0129065726500140","DOIUrl":"10.1142/S0129065726500140","url":null,"abstract":"<p><p>Relieving driver fatigue is crucial for ensuring traffic safety. Existing research lacks an exploration of the feasibility and effectiveness of using implicit emotion modulation methods to alleviate driver fatigue. In this study, the effects of Emotional Sensory (olfactory or olfactory-auditory) Stimuli (ESS) on modulating driver fatigue are explored, and the underlying neural mechanisms are analyzed based on the spatio-temporal dynamic patterns of Electroencephalogram (EEG) signals. First, a real-world driver fatigue modulation experiment based on ESS was designed to record EEG signals. Second, brain activation patterns under various ESS were investigated by analyzing brain functional networks. Furthermore, dynamic changes in fatigue-related features were analyzed to examine the strength and persistence of driver fatigue modulation for each ESS. Finally, a fatigue similarity measure method was adopted to quantify the fatigue recovery level under ESS in a more intuitive manner. The results demonstrate that the mint odor-High-Arousal-Low-Valence (HALV) music stimulus exhibits the best driver fatigue modulation effects, and is superior to singular olfactory stimuli. Furthermore, dynamic brain functional connectivity analysis reveals that effective driver fatigue modulation tends to be strongly synchronized in the frontal and parietal lobes. The optimal olfactory-auditory mixed stimuli restores driver fatigue to the level 58-60[Formula: see text]min ago. Our findings shed light on the dynamic characterization of functional connectivity during driver fatigue modulation and demonstrate the potential of using ESS as a reliable implicit tool for modulating driver fatigue.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650014"},"PeriodicalIF":6.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146069412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}