Neural Computation最新文献_第2页

Associative Emotional Learning in Convolutional Neural Networks. 卷积神经网络中的联想情绪学习。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-09-22 DOI: 10.1162/NECO.a.1580

Seowung Leem, Andreas Keil, Mingzhou Ding, Ruogu Fang

{"title":"Associative Emotional Learning in Convolutional Neural Networks.","authors":"Seowung Leem, Andreas Keil, Mingzhou Ding, Ruogu Fang","doi":"10.1162/NECO.a.1580","DOIUrl":"https://doi.org/10.1162/NECO.a.1580","url":null,"abstract":"<p><p>Associative emotional learning enables organisms to adaptively link pleasant or unpleasant outcomes to the presence of predictive stimuli. Whereas computational models such as the Rescorla-Wagner model have shed light on this important function, the limitations of these models are also known, especially when they are applied to neural data. The advent of deep neural networks has opened another avenue for modeling associative emotional learning. In this work, we proposed a deep neural network model of visual valence processing, consisting of a visual module that encodes complex natural scenes and a module that recognizes their emotional significance in terms of valence, a key dimension of emotion, and tested a novel Pavlovian learning paradigm on the model. The results showed that with learning, the model reproduced several observations from human associative learning studies, including association formation and generalization, and that the neural representations of the conditioned and the unconditioned stimuli became increasingly aligned at both the single unit and the neural population level. Comparison between the model and human experimental data provided further validation of our approach. This study thus suggests that deep neural network models, when combined with appropriate learning algorithms, can be used to model behavioral and neural signatures of associative emotion/valence learning.</p>","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":" ","pages":"1-28"},"PeriodicalIF":2.1,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149026682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Teaching Signal Synchronization in Deep Neural Networks With Prospective Neurons 具有前瞻神经元的深度神经网络教学信号同步。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-09-18 Epub Date: 2026-09-28 DOI: 10.1162/NECO.a.1571

Nicolas Zucchet;Qianqian Feng;Axel Laborieux;Friedemann Zenke;Walter Senn;João Sacramento

{"title":"Teaching Signal Synchronization in Deep Neural Networks With Prospective Neurons","authors":"Nicolas Zucchet;Qianqian Feng;Axel Laborieux;Friedemann Zenke;Walter Senn;João Sacramento","doi":"10.1162/NECO.a.1571","DOIUrl":"10.1162/NECO.a.1571","url":null,"abstract":"Working memory requires the brain to maintain information from the recent past to guide ongoing behavior. Neurons can contribute to this capacity by slowly integrating their inputs over time, creating persistent activity that outlasts the original stimulus. However, when these slowly integrating neurons are organized hierarchically, they introduce cumulative delays that create a fundamental challenge for learning: teaching signals that indicate whether behavior was correct or incorrect arrive out-of-sync with the neural activity they are meant to instruct. Here, we demonstrate that neurons enhanced with an adaptive current can compensate for these delays by responding to external stimuli prospectively, effectively predicting future inputs to synchronize with them. First, we show that such prospective neurons enable teaching signal synchronization across a range of learning algorithms that propagate error signals through hierarchical networks. Second, we demonstrate that this successfully guides learning in slowly integrating neurons, enabling the formation and retrieval of memories over extended timescales. We support our findings with a mathematical analysis of the prospective coding mechanism and learning experiments on motor control tasks. Together, our results reveal how neural adaptation could solve a critical timing problem and enable efficient learning in dynamic environments.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 10","pages":"1785-1828"},"PeriodicalIF":2.1,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148763135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Simple Encoder Training for Hyperdimensional Computing 简单编码器训练的超维计算。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-09-18 Epub Date: 2026-09-28 DOI: 10.1162/NECO.a.1567

Peter Kirby;Laura Smets;Werner Van Leekwijck;José Oramas

引用次数: 0

Extending a Formal Model of Predictive Coding to Human Spoken Word Recognition 预测编码的形式化模型在人类口语单词识别中的扩展。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-09-18 Epub Date: 2026-09-28 DOI: 10.1162/NECO.a.1570

Bryce Rogers;Monica Yi-Chen Li;Thomas Hannagan;James S. Magnuson;Kevin S. Brown

{"title":"Extending a Formal Model of Predictive Coding to Human Spoken Word Recognition","authors":"Bryce Rogers;Monica Yi-Chen Li;Thomas Hannagan;James S. Magnuson;Kevin S. Brown","doi":"10.1162/NECO.a.1570","DOIUrl":"10.1162/NECO.a.1570","url":null,"abstract":"There is a general consensus in theories of human speech recognition that humans engage in predictive processing during online speech processing. There are also claims that predictive processing is indicative of the operation of a predictive coding (PC) mechanism. PC is a generative, hierarchical feedback framework where feedback signals consist of input predictions, while feedforward signals consist primarily of prediction errors (PE). Some researchers have taken decreased neural signals when inputs conform to expectations as evidence for PC and claim that other possible explanatory frameworks (e.g., interactive activation) are incompatible with reported reductions in PE. However, these claims have been advanced using narrow-scope computational implementations of PC without known abilities to adequately (i.e., plausibly) simulate broader human spoken word recognition (SWR) behavioral phenomena. Here, we present the first known neurally and behaviorally adequate, mathematically formal neural network PC model of time-dependent human SWR. After demonstrating that the new model is able to emulate a fundamental, empirical signature of human SWR behavior (time course of lexical activation and competition), we compare model dynamics to neural performance targets that have been touted as hallmarks of PC in SWR. While the new model readily exhibits predictive processing (anticipatory activation of phonemes consistent with lexical knowledge) and reduced neural activity when inputs match expectations (a necessary component of PC) more subtle patterns of neural activity under priming and noise conditions, previously proposed as diagnostic of PC do not emerge appreciably. This suggests that such patterns may not be hallmarks of PC. We discuss implications for PC-based theories of SWR.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 10","pages":"1872-1911"},"PeriodicalIF":2.1,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148763292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Twin Network Augmentation: A Novel Training Strategy for Improved Spiking Neural Networks and Weight Quantization 孪生网络增强：一种改进尖峰神经网络和权量化的新训练策略。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-09-18 Epub Date: 2026-09-28 DOI: 10.1162/NECO.a.1568

Lucas Deckers;Benjamin Vandersmissen;Ing Jyh Tsang;Werner Van Leekwijck;Steven Latré

{"title":"Twin Network Augmentation: A Novel Training Strategy for Improved Spiking Neural Networks and Weight Quantization","authors":"Lucas Deckers;Benjamin Vandersmissen;Ing Jyh Tsang;Werner Van Leekwijck;Steven Latré","doi":"10.1162/NECO.a.1568","DOIUrl":"10.1162/NECO.a.1568","url":null,"abstract":"The proliferation of artificial neural networks (ANNs) has led to increased energy consumption, raising concerns about their sustainability. Spiking neural networks (SNNs) operate using sparse, binary spikes to communicate information between neurons and offer a potential solution due to their limited energy requirements. Another technique for reducing a neural network’s footprint is quantization, which compresses weight representations to decrease memory usage and energy consumption. In this study, we present twin network augmentation (TNA), a novel training method aimed at improving the performance of SNNs on a range of benchmark data sets while also facilitating enhanced network compression through quantization of weights. TNA involves cotraining an SNN with a twin SNN with identical network architecture, optimizing both networks to minimize their cross-entropy losses and the mean squared error between their output logits. We demonstrate that TNA significantly enhances classification performance across various data sets and can be applied for reducing SNNs to ternary weight precision for inference. Our results show that TNA outperforms traditional knowledge distillation methods and achieves state-of-the-art performance for the evaluated network architecture on benchmark data sets, including CIFAR-10, CIFAR-100, and CIFAR-10-DVS. This letter underscores the effectiveness of TNA in bridging the performance gap between SNNs and ANNs and suggests further exploration into the application of TNA on different network architectures and data sets.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 10","pages":"1850-1871"},"PeriodicalIF":2.1,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148765521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Time Constant Rule for Neural Change Detection 神经变化检测的时间常数规则。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-09-18 Epub Date: 2026-09-28 DOI: 10.1162/NECO.a.1569

Travis Monk;Shivaram Mani;Paul Hurley;André van Schaik

{"title":"The Time Constant Rule for Neural Change Detection","authors":"Travis Monk;Shivaram Mani;Paul Hurley;André van Schaik","doi":"10.1162/NECO.a.1569","DOIUrl":"10.1162/NECO.a.1569","url":null,"abstract":"Sensory pathways differ widely across species and modalities in anatomy and function. Yet many solve variants of the same ancient, pervasive problem: quickly detecting meaningful changes in the world. Sometimes animals need to make these detections from noisy signals with millisecond precision to survive. We suggest how a single spiking neuron can address this selection pressure for quick detection. We present a simple relationship linking neural voltage dynamics to online hypothesis testing that we call the time constant rule. Assume that a neuron’s membrane time constant equals the inverse of a change in its input rate. We show that this rule is then necessary and sufficient for its subthreshold membrane potential to represent a likelihood ratio of that rate change. Thresholding that likelihood ratio makes the neuron an online detector of input rate increases and, by extension, stimulus onset when rapid reaction is required. We tested the time constant rule by reanalyzing published recordings from eight second-order sensory neurons spanning olfaction, mechanoreception, electroreception, and audition, across both insects and vertebrates. In all cases, the measured membrane time constants were consistent with the predicted inverse relationship. These examples are intended as cross-system and cross-phyla consistency checks rather than a population-level validation study. When the time constant rule holds, it yields a direct and intuitive interpretation of neural computation. A neuron’s voltage is an online likelihood ratio: its time constant sets the decay of statistical evidence, its threshold is a decision line, and each output spike is a time-stamped declaration that its input statistics have changed. The rule links membrane biophysics with the statistical computation and ecological function of a neuron. Its falsifiability invites direct experimental tests to determine whether it extends more broadly across sensory pathways and neuron classes.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 10","pages":"1753-1784"},"PeriodicalIF":2.1,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11713462","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148766657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Neuronal Spike Trains as Functional-Analytic Distributions: Representation, Analysis, and Significance 神经元尖峰序列作为功能分析分布：表征、分析和意义。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-08-21 Epub Date: 2026-08-27 DOI: 10.1162/NECO.a.1564

Gabriel A. Silva

引用次数: 0

Shape Matters: Few-Shot Object Classification From High-Information Contour Features 形状问题：基于高信息轮廓特征的少镜头目标分类。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-08-21 Epub Date: 2026-08-27 DOI: 10.1162/NECO.a.1563

Maria Osório;Alexandre Bernardino;Andreas Wichert

{"title":"Shape Matters: Few-Shot Object Classification From High-Information Contour Features","authors":"Maria Osório;Alexandre Bernardino;Andreas Wichert","doi":"10.1162/NECO.a.1563","DOIUrl":"10.1162/NECO.a.1563","url":null,"abstract":"A key challenge in visual object recognition is developing models that generalize from limited data while maintaining transparency in their decision making. We propose a biologically inspired model that addresses both issues by classifying images based on transformation-invariant local shape key features. Following the principles of the brain’s what and where pathways, each feature is encoded by an image patch and its relative location in polar coordinates, enabling interpretable and robust comparisons between inputs and class prototypes. To mimic human concept learning, prototypes are selected using clustering, improving representativeness and generalization. Results show that our model achieves human-comparable performance, with an error rate between 1% and 2% on the MNIST data set when all training images are used as prototypes. In data-limited scenarios, where only a small number of prototypes are selected, our model consistently outperforms convolutional neural networks (CNNs). To evaluate out-of-distribution generalization, we use prototypes from MNIST and test both models on the ETL-1 data set, which differs in data distribution. Although CNN accuracy drops significantly under these conditions, our model maintains high accuracy, even with few prototypes, demonstrating strong robustness and greater capacity to generalize to unseen distributions, bringing it closer to human-like recognition capabilities.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 9","pages":"1611-1632"},"PeriodicalIF":2.1,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148649881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Associative Memory and Generative Diffusion in the Zero-Noise Limit 零噪声极限下的联想记忆与生成扩散。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-08-21 Epub Date: 2026-08-27 DOI: 10.1162/NECO.a.1565

Joshua Hess;Quaid Morris

{"title":"Associative Memory and Generative Diffusion in the Zero-Noise Limit","authors":"Joshua Hess;Quaid Morris","doi":"10.1162/NECO.a.1565","DOIUrl":"10.1162/NECO.a.1565","url":null,"abstract":"This letter shows that generative diffusion processes converge to associative memory systems at vanishing noise levels and characterizes the stability, robustness, memorization, and generation dynamics of both model classes. Morse-Smale dynamical systems are shown to be universal approximators of associative memory models, with diffusion processes as their white-noise perturbations. The universal properties of associative memory that follow are used to characterize a generic transition from generation to memory as noise diminishes. The structural stability of Morse-Smale flows—that is, the robustness of their global critical point structure—implies the stability of both trajectories and invariant measures for diffusions in the zero-noise limit. The learning and generation landscapes of these models appear as parameterized families of gradient flows and their stochastic perturbations, and the bifurcation theory for Morse-Smale systems implies that they are generically stable except at isolated parameter values, where enumerable sets of local and global bifurcations govern transitions between stable systems. These landscapes are thus characterized by ordered bifurcation sequences that create, destroy, or alter connections between rest points and are robust under small stochastic or deterministic perturbations. The framework is agnostic to model formulation, which we verify with examples from energy-based models, denoising diffusion models, and classical and modern Hopfield networks. We additionally derive structural stability criteria for Hopfield-type networks and find that simple cases violate them. Collectively, our geometric approach provides insight into the classification, stability, and emergence of memory and generative landscapes.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 9","pages":"1658-1751"},"PeriodicalIF":2.1,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148649779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unsupervised Feature Selection Using Bayesian Tucker Decomposition 基于贝叶斯塔克分解的无监督特征选择。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-08-21 Epub Date: 2026-08-27 DOI: 10.1162/NECO.a.1554

Y-h. Taguchi;Yoh-ichi Mototake

引用次数: 0