Neural Computation最新文献_第3页

Hierarchical Active Inference Using Successor Representations 使用后继表示的分层主动推理。

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.1545

Prashant Rangarajan;Rajesh P. N. Rao

{"title":"Hierarchical Active Inference Using Successor Representations","authors":"Prashant Rangarajan;Rajesh P. N. Rao","doi":"10.1162/NECO.a.1545","DOIUrl":"10.1162/NECO.a.1545","url":null,"abstract":"Active inference, a neurally inspired model for inferring actions based on the free energy principle (FEP), has been proposed as a unifying framework for understanding perception, action, and learning in the brain. Active inference has previously been used to model ecologically important tasks such as navigation and planning, but scaling it to solve complex large-scale problems in real-world environments has remained a challenge. Inspired by the existence of multiscale hierarchical representations in the brain, we propose a model for planning actions based on hierarchical active inference. Our approach combines a hierarchical model of the environment with successor representations for efficient planning. We present results demonstrating (1) how lower-level successor representations can be used to learn higher-level abstract states, (2) how planning based on active inference at the lower level can be used to bootstrap and learn higher-level abstract actions, and (3) how these learned higher-level abstract states and actions can facilitate efficient planning. We illustrate the performance of the approach on several planning and reinforcement learning (RL) problems, including a variant of the well-known four rooms task, a key-based navigation task, a partially observable planning problem, the mountain car problem, and PointMaze, a family of navigation tasks with continuous state and action spaces. Our results represent, to our knowledge, the first application of learned hierarchical state and action abstractions to active inference in FEP-based theories of brain function.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 9","pages":"1491-1544"},"PeriodicalIF":2.1,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148303987","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

Quantifying Information Stored in Synaptic Connections Rather Than in Firing Activities of Neural Networks 量化存储在突触连接而不是神经网络发射活动中的信息。

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.1566

Xinhao Fan;Shreesh P. Mysore

{"title":"Quantifying Information Stored in Synaptic Connections Rather Than in Firing Activities of Neural Networks","authors":"Xinhao Fan;Shreesh P. Mysore","doi":"10.1162/NECO.a.1566","DOIUrl":"10.1162/NECO.a.1566","url":null,"abstract":"A cornerstone of our understanding of both biological and artificial neural networks is that they store information in the strengths of synaptic connections among the neurons. However, in contrast to the well-established theory for quantifying information encoded by the firing activity of neural networks, there does not exist a framework for quantifying information stored in the distribution of synaptic connection weights. Here, we develop a theoretical framework for synaptic information, by using densely connected Hebbian networks performing autoassociative memory tasks as the substrate, and by modeling data patterns that need to be stored as log-normal distributions. Specifically, we derive analytical approximations for Shannon mutual information between the data patterns and singletons, pairs, and arbitrary n-tuples of synaptic connections within the network. Our framework corroborates well-established insights regarding pattern storage capacity and the principle of distributed coding in neural firing activities. Notably, it formalizes the heterogeneity inherent in information encoding across synapses in a network, and discovers synergistic interactions among synapses, revealing that the information encoded jointly by all the synapses exceeds the sum of its parts. Taken together, this study introduces a powerful, interpretable framework for quantitatively understanding information storage in the synapses of neural networks, one that illustrates the duality of synaptic connectivity and neural population activity in learning and memory.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 9","pages":"1545-1578"},"PeriodicalIF":2.1,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148649851","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

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning DROP：强化学习的分布和规则乐观主义和悲观主义。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-07-27 Epub Date: 2026-08-06 DOI: 10.1162/NECO.a.1546

Taisuke Kobayashi

{"title":"DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning","authors":"Taisuke Kobayashi","doi":"10.1162/NECO.a.1546","DOIUrl":"10.1162/NECO.a.1546","url":null,"abstract":"In reinforcement learning (RL), temporal difference (TD) error is known to be related to the firing rate of dopamine neurons. It has been observed that each dopamine neuron does not behave uniformly, but each responds to the TD error in an optimistic or pessimistic manner, interpreted as a kind of distributional RL. To explain such biological data, a heuristic model has also been introduced with learning rates asymmetric for the positive and negative TD errors. However, this heuristic model is not theoretically grounded, and it is unknown whether it can work as an RL algorithm. This letter therefore introduces a novel theoretically grounded model with optimism and pessimism, which is derived from control as inference. In combination with ensemble learning, a distributional value function as a critic is estimated from regularly introduced optimism and pessimism. Based on its central value, a policy in an actor is improved. This proposed algorithm, so-called DROP (distributional and regular optimism and pessimism), is compared on dynamic tasks. Although the heuristic model showed poor learning performance, DROP demonstrated excellent performance in all tasks with high generality. In addition, DROP achieved learning performance comparable to the state-of-the-art algorithms. In other words, it was suggested that DROP is a new model that can elicit the potential contributions of optimism and pessimism.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 8","pages":"1376-1407"},"PeriodicalIF":2.1,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148303940","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

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling 不确定条件下序列抽样决策的无模型强化学习实现。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-07-27 Epub Date: 2026-08-06 DOI: 10.1162/NECO.a.1543

Jamal Esmaily;Rani Moran;Yasser Roudi;Bahador Bahrami

引用次数: 0

Cross-Frequency Coupling as a Neural Substrate for Prediction Error Evaluation: A Laminar Neural Mass Modeling Approach 交叉频率耦合作为预测误差评估的神经基质：层流神经团建模方法。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-07-27 Epub Date: 2026-08-06 DOI: 10.1162/NECO.a.1537

Giulio Ruffini;Edmundo Lopez-Sola;Raul Palma;Roser Sanchez-Todo;Jakub Vohryzek;Francesca Castaldo;Karl Friston

{"title":"Cross-Frequency Coupling as a Neural Substrate for Prediction Error Evaluation: A Laminar Neural Mass Modeling Approach","authors":"Giulio Ruffini;Edmundo Lopez-Sola;Raul Palma;Roser Sanchez-Todo;Jakub Vohryzek;Francesca Castaldo;Karl Friston","doi":"10.1162/NECO.a.1537","DOIUrl":"10.1162/NECO.a.1537","url":null,"abstract":"Predictive coding frameworks suggest neural computations rely on hierarchical error minimization, yet the neural implementation of this inference remains unclear. We propose that cross-frequency coupling (CFC) furnishes fundamental mechanism for this process. Using our laminar neural mass model (LaNMM), we demonstrate that signal-envelope coupling (SEC) an envelope-envelope coupling (EEC) instantiate a hierarchical comparator mechanism. Specifically, SEC generates prediction-error signals by subtracting top-down predictions from bottom-up oscillatory envelopes, while EEC operates at slower timescales to implement gating—a critical mechanism for precision weighting. To establish the face validity and clinical implications of this proposal, we model perturbations of these CFC mechanisms to investigate their roles in pathophysiological and altered neuronal function. In Alzheimer’s disease, interneuron dysfunction disrupts the comparator, causing aberrant prediction error amplification in early stages and drastic attenuation in late phases. Conversely, serotonergic psychedelics increase excitatory gain, diminishing the modulatory effect of predictions and causing a failure of sensory attenuation. Collectively, these findings implicate multiscale cross-frequency coupling as a key computational mechanism supporting predictive coding and its disruption in disease.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 8","pages":"1299-1343"},"PeriodicalIF":2.1,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148610128","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

A Hidden Markov Model–Inspired Sequence Classification Method for Hyperdimensional Computing 一种基于隐马尔可夫模型的超维序列分类方法。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-07-27 Epub Date: 2026-08-06 DOI: 10.1162/NECO.a.1544

Krzysztof Ślot;Jakub Bednarski;Kacper Kubicki;Piotr Łuczak

{"title":"A Hidden Markov Model–Inspired Sequence Classification Method for Hyperdimensional Computing","authors":"Krzysztof Ślot;Jakub Bednarski;Kacper Kubicki;Piotr Łuczak","doi":"10.1162/NECO.a.1544","DOIUrl":"10.1162/NECO.a.1544","url":null,"abstract":"This letter introduces a novel method for discrete-sequence classification within the hyperdimensional computing (HDC) paradigm. The method, inspired by the concept of hidden Markov models (HMM), implements mechanisms that effectively address the major challenges arising in analyzing sequences generated by real-world processes, such as variable length, misalignment, symbol repetitions, omissions, or insertions. All algebraic transformations of input data in HMM-based sequence classification are replaced by bitwise operations on appropriately derived hyperdimensional binary vectors (hypervectors). The proposed hypervector transformation pipeline mirrors the algebraic manipulations of the HMM paradigm and involves a procedure that prevents information decay when processing longer sequences. Since only binary bit-wise operations on hypervectors are used in computations, the proposed method is well suited for hardware implementation, especially in the form of custom in-memory computing VLSI devices. The experimental evaluation of the proposed method, conducted on both artificial and real-world data sets, demonstrates its superiority over existing HDC-based sequence analysis approaches, yielding noticeable gains in classification accuracy. We also demonstrate that the proposed approach, like most HDC-based sequence classification methods, is robust against adverse physical, internal, or external factors that induce bit flips in the underlying hardware, which could entirely corrupt the outcomes of classical sequence-analysis methods, such as HMMs.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 8","pages":"1469-1489"},"PeriodicalIF":2.1,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148303934","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

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators 贝叶斯估计频率估计的w核及其主空间。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-07-27 Epub Date: 2026-08-06 DOI: 10.1162/NECO.a.1547

Yukito Iba

{"title":"W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators","authors":"Yukito Iba","doi":"10.1162/NECO.a.1547","DOIUrl":"10.1162/NECO.a.1547","url":null,"abstract":"Evaluating the variability of posterior estimates is a key aspect of Bayesian model assessment. In this study, we focus on the posterior covariance matrix W, defined through the log likelihoods of individual observations. Previous studies, notably MacEachern and Peruggia (2002) and Thomas et al. (2018), examined the role of the principal space of W in Bayesian sensitivity analysis. Here, we show that the principal space of W is also central to frequentist evaluation, using the recently proposed Bayesian infinitesimal jackknife (Bayesian IJ) approximation (Giordano & Broderick, 2023) as a key tool. We further clarify the relationship between W and the Fisher kernel, showing that a modified version of the Fisher kernel can be viewed as an approximation to W. Moreover, the matrix W itself can be interpreted as a reproducing kernel, which we refer to as the W-kernel. Based on this connection, we investigate the relation between the W-kernel formulation in the data space and the classical asymptotic formulation in the parameter space. We also introduce the matrix Z, which is effectively dual to W in the sense of PCA; this formulation provides another perspective on the relationship between W and classical asymptotic theory. In the appendixes, we explore approximate bootstrap methods for posterior means and show that projection onto the principal space of W facilitates frequentist evaluation when higher-order terms are included. In addition, we introduce incomplete Cholesky decomposition as an efficient method for computing the principal space of W and discuss the concept of representative subsets of observations.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 8","pages":"1408-1468"},"PeriodicalIF":2.1,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148304052","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

Domain Adaptation With Additional Features via Label-Aware and Graph-Based Fused Gromov–Wasserstein Optimal Transport 基于标签感知和基于图的融合Gromov-Wasserstein最优传输的领域自适应。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-06-02 Epub Date: 2026-06-17 DOI: 10.1162/NECO.a.1525

Toshimitsu Aritake;Hideitsu Hino

{"title":"Domain Adaptation With Additional Features via Label-Aware and Graph-Based Fused Gromov–Wasserstein Optimal Transport","authors":"Toshimitsu Aritake;Hideitsu Hino","doi":"10.1162/NECO.a.1525","DOIUrl":"10.1162/NECO.a.1525","url":null,"abstract":"In many domain adaptation tasks, the source and target domains share an identical feature space, so the domain gap arises only from the distributional shift. In practice; however, new-target-only features (e.g., sensors added after training) often become available at test time, violating the shared feature space assumption and invalidating most existing methods. We address this setting with Label-Aware and Graph-Based Fused Gromov-Wasserstein Optimal Transport (LAGB-FGW), focusing on a transductive domain adaptation scenario, in which the entire unlabeled target data set is available during training, and predictions are jointly inferred for all target samples. LAGB-FGW (1) embeds label discrepancy directly into the source metric, (2) constructs a K-NN graph on the full target feature space to capture structure introduced by the additional features, and (3) jointly solves standard Optimal Transport (OT) and Gromov-Wasserstein OT, thereby transferring labels using both the common and the additional features. We validate LAGB-FGW on four synthetic benchmarks and the HAR70+ human-activity data set, and LAGB-FGW consistently outperforms all baselines, highlighting the advantage of combining source label information with graph-based structural cues when additional target features are available only at test time.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 7","pages":"1203-1232"},"PeriodicalIF":2.1,"publicationDate":"2026-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147789401","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

Autonomous Learning With High-Dimensional Computing Architecture Similar to Von Neumann's 与冯·诺伊曼的高维计算架构类似的自主学习。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-06-02 Epub Date: 2026-06-17 DOI: 10.1162/NECO.a.1523

Pentti Kanerva

{"title":"Autonomous Learning With High-Dimensional Computing Architecture Similar to Von Neumann's","authors":"Pentti Kanerva","doi":"10.1162/NECO.a.1523","DOIUrl":"10.1162/NECO.a.1523","url":null,"abstract":"We model human and animal learning by computing with high-dimensional vectors (e.g., D = 10,000). The architecture resembles traditional (von Neumann) computing with numbers, but the instructions refer to vectors and operate on them in superposition. The architecture includes a high-capacity memory for vectors, counterpart of the random-access memory (RAM) for numbers. The model's ability to learn from data reminds us of deep learning, but with an architecture closer to biology. The architecture agrees with an idea from psychology that human memory and learning involve a short-term working memory and a long-term data store. Neuroscience provides us with a model of the long-term memory, namely, the cortex of the cerebellum. With roots in psychology, biology, and traditional computing, a theory of computing with vectors can help us understand how brains compute. Application to learning by robots seems inevitable, but there is likely to be more, including language. Ultimately we want to compute with no more material and energy than brains use. To that end, we need a mathematical theory that agrees with psychology and biology and is suitable for nano-technology. We also need to exercise the theory in large-scale experiments. The analogy with traditional computing suggests that the architecture be programmable in terms of variables, values, and data structures, the very things that have made traditional computing ubiquitous and that seem worth learning from and emulating.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"38 7","pages":"1117-1134"},"PeriodicalIF":2.1,"publicationDate":"2026-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147789278","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

Global Stability of a Hebbian/Anti-Hebbian Network for Principal Subspace Learning 主子空间学习的Hebbian/Anti-Hebbian网络的全局稳定性。

IF 2.1 4区计算机科学

Neural Computation Pub Date : 2026-06-02 Epub Date: 2026-06-17 DOI: 10.1162/NECO.a.1524

David Lipshutz;Robert J. Lipshutz

引用次数: 0