NEUROCOMPUTING神经计算
NEUROCOMPUTING(英文缩写 NEUROCOMPUTING),ISSN 0925-2312,eISSN 1872-8286,中文译名:神经计算 是一本学术期刊。本页汇总该期刊的最新影响因子、分区信息以及最新收录于 PubMed 的文献,帮助您快速了解期刊全貌。
发文量统计区间：2025-09-27 至 2026-09-27，按本站收录文献的发表日期统计。
期刊介绍
历年影响因子趋势
| JCR 数据年份 | 影响因子 | JCR 分区 |
|---|---|---|
| 2021 | 5.779 | Q2 |
| 2022 | 6.000 | Q2 |
| 2023 | 5.500 | Q1 |
| 2024 | 6.500 | Q1 |
| 2025 | 6.700 | Q1 |
NEUROCOMPUTING 最新收录文献
-
1. Automated Behavior Analysis in the Novel Object Recognition Test.
PMID:日期:2026-10-07Accurate identification of animal behaviors is fundamental to behavioral neuroscience, yet manual annotation remains a major bottleneck due to its subjectivity, limited scalability, and high labor cost. This work presents a unified deep learning and heuristic-based framework for automated behavior classification in the Novel Object Recognition Test (NORT), a widely used paradigm for assessing memory and cognitive function in rodents. We fine-tuned a YOLOv11 Pose model to detect and keypoints specific to Long-Evans rats, and used these keypoints to derive spatial heuristics for identifying NORT behaviors. In parallel, we trained YOLOv11 classification models to predict , and behaviors from individual frames, using datasets containing either 2-object or 5-object videos, as well as a combined dataset containing both 2-object and 5-object videos. Our model trained on the combined dataset, enhanced with heuristic-based post-processing to identify the specific objects that the rat is interacting with, achieved the best overall accuracy and generalization across arenas, outperforming heuristic-only and subset-specific 2-object or 5-object models. Detailed confusion matrices and error analyses reveal that most errors occur near behavioral transitions, reflecting the inherent ambiguity of manual labels at frame-level. The proposed framework enables scalable, reproducible, and objective annotation of NORT videos and provides a foundation for future extensions toward temporally-aware behavioral analysis. All the code and model weights, together with sample NORT videos, will be made publicly available to support future rodent behavior recognition research.
-
2. CrunchLLM: Multitask LLMs for Structured Business Reasoning and Outcome Prediction.
PMID:日期:2026-07-14Predicting the success of startup companies, defined as achieving an exit through acquisition or IPO, is a critical problem in entrepreneurship and innovation research. Datasets such as Crunchbase provide both structured information (e.g., funding rounds, industries, and investor networks) and unstructured text (e.g., company descriptions), but effectively leveraging such heterogeneous data for prediction remains challenging. Traditional machine learning approaches often rely only on structured features and achieve moderate accuracy, while large language models (LLMs) offer strong reasoning capabilities but are not readily adapted to domain-specific business data. We present , a domain-adapted and backbone-agnostic LLM framework for startup success prediction. CrunchLLM integrates structured company attributes with unstructured textual narratives and applies parameter-efficient fine-tuning together with prompt optimization to specialize foundation models for entrepreneurship data. Importantly, our framework introduces a self-verifiable multitask objective, in which the justification loss serves as a training-time constraint on classification, together with a hierarchically ordered input encoding that reduces the tendency of long unstructured company narratives to overshadow structured business attributes. These methodological innovations yield more reliable and feature-grounded predictions than conventional prompt-based LLM adaptation. Our approach achieves 89% accuracy on the Crunchbase startup success prediction task, significantly outperforming traditional classifiers and baseline LLMs. Beyond predictive performance, CrunchLLM generates interpretable reasoning traces that support its predictions, enhancing transparency and trustworthiness for financial and policy decision-makers. Overall, this work demonstrates how domain-aware LLM adaptation and structured-unstructured data fusion can advance predictive modeling of entrepreneurial outcomes, providing both a methodological framework and a practical tool for data-driven decision-making in venture capital and innovation policy.
-
3. GNN-EGG: Graph neural network explanations via graph generation.
PMID:日期:2026-06-07Graph Neural Networks (GNNs) provide a means for modeling inherently graphical data, such as transportation, social, and molecular networks, but also for enhancing and reducing unstructured data, including text and images. A potential shortcoming is that their predictions are opaque-a black box-hindering broader adoption and refinement. In this paper, we propose a novel architecture-agnostic algorithm, GNN-EGG (Graph Neural Network Explanations via Graph Generation), for GNN classifiers. As a model-level post-hoc explanation method, GNN-EGG can learn the data generating distribution for each class of graphs. The primary contribution of this work is the use of a differentiable approximation to Graph Edit Distance (GED) in the loss function. This term enables us to ensure consistency in both the graph space and the embedding space for our representative examples. It also reduces the random baseline issue where completely random graphs can still yield similar embeddings and strong predictions as reported in previous work. We benchmark our algorithm against the current state-of-the-art models using the mutagenic molecules dataset (MUTAG) and apply our method to a large-scale GNN for malignancy detection in digital pathology tasks. The official implementation of this method can be found at this GitHub repository.
-
4. Decoding pre-movement neural activity from thalamic LFPs for adaptive neurostimulation in tremor patients.
PMID:日期:2026-04-14To advance adaptive deep brain stimulation for tremor disorders, we investigated the feasibility of using machine learning to decode pre-movement oscillatory changes in thalamic local field potentials (LFPs) and scalp electroencephalography (EEG) signals. Our aim was to predict upcoming upper-limb movements based on these neural signals. We recorded and analysed from 11 patients undergoing deep brain stimulation surgery for the treatment of tremor, employing machine learning models-including logistic regression, gradient-boosted decision trees, and convolutional neural networks-to distinguish rest periods from pre-movement periods. We demonstrate that early neural correlates can predict movement onset, achieving above-chance decoding performance starting approximately 430 ms before movement initiation using thalamic LFP and 840 ms using EEG signals. Individualised, patient-specific decoders outperformed cross-patient models, reflecting inter-patient variability in neural modulatory patterns. Additionally, multiple frequency bands contributed independently to decoding performance, highlighting the importance of incorporating a spectrum of frequencies rather than relying solely on activity in any single canonical band. These findings underscore the value of personalised, multi-band machine learning-based approaches for capturing the neural correlates preceding movement. They support the development of adaptive neurostimulation therapies through tailored models that account for patient-specific patterns in neural activity.
-
5. SymRefine: A symbolic regression approach for refining and compressing neural networks.
PMID:日期:2026-04-01Traditional methods for compressing neural networks (NN), such as pruning and distillation, primarily focus on reducing the size of the NN, often at the expense of accuracy. To overcome this limitation, we propose a novel refining NN method based on symbolic regression called SymRefine. SymRefine constructs a Cartesian genetic programming linear method (LCGP) to identify the mathematical expression that represents the relationship between the high-dimensional input and output of a selected module within the NN. The effectiveness of SymRefine was tested using two types of NN benchmarks: multilayer perceptron NNs (MLP) and convolutional NNs (CNN). Experimental results show that, compared with NN pruning and NN distillation, SymRefine can effectively reduce the number of the NN parameters while maintaining or even enhancing inference accuracy. This research demonstrates the potential of SymRefine as a novel tool for creating more efficient and accurate neural networks.
-
6. Deep Learning for analyzing chaotic dynamics in biological time series: Insights from frog heart signals.
PMID:日期:2026-01-07The study of experimental data is a relevant task in several physical, chemical and biological applications. In particular, the analysis of chaotic dynamics in cardiac systems is crucial as it can be related to certain pathological arrhythmias. When working with short and noisy experimental time series, some standard techniques for chaos detection cannot provide reliable results because of such data characteristics. Moreover, when small datasets are available, some Deep Learning techniques cannot be applied directly (that is, using part of the data to train the network, and using the trained network to analyze the remaining dataset). To overcome all these limitations, we propose an automatic algorithm that combines Deep Learning and some selection strategies based on a mathematical model of the same nature of the experimental data. To demonstrate its performance, we test it with experimental data obtained from ex-vivo frog heart experiments, achieving highly accurate results.
-
7. Explaining Graph Neural Networks with Mixed-Integer Programming.
PMID:日期:2025-07-28Graph Neural Networks (GNNs) provide state-of-the-art graph learning performance, but their lack of transparency hinders our ability to understand and trust them, ultimately limiting the areas where they can be applied. Many methods exist to explain individual predictions made by GNNs, but there are fewer ways to gain more general insight into the patterns they have been trained to identify. Most existing methods for model-level GNN explanations attempt to generate graphs that exemplify these patterns, but the discreteness of graphs and the nonlinearity of deep GNNs make finding such graphs difficult. In this paper, we formulate the search for an explanatory graph as a mixed-integer programming (MIP) problem, in which decision variables specify the explanation graph and the objective function represents the quality of the graph as an explanation for a GNN's predictions of an entire class in the dataset. This approach, which we call MIPExplainer, allows us to directly optimize over the discrete input space and find globally optimal solutions with a minimal number of hyperparameters. MIPExplainer outperforms existing methods in finding accurate and stable explanations on both synthetic and real-world datasets. Code is available at https://github.com/blake-gaines/MIPExplainer.
-
8. Artificial intelligence without restriction surpassing human intelligence with probability one: Theoretical insight into secrets of the brain with AI twins of the brain.
PMID:日期:2025-02-28Artificial Intelligence (AI) has apparently become one of the most important techniques discovered by humans in history while the human brain is widely recognized as one of the most complex systems in the universe. One fundamental critical question which would affect human sustainability remains open: Will artificial intelligence (AI) evolve to surpass human intelligence in the future? This paper shows that in theory new AI twins with fresh cellular level of AI techniques for neuroscience could approximate the brain and its functioning systems (e.g. perception and cognition functions) with any expected small error and AI without restrictions could surpass human intelligence with probability one in the end. This paper indirectly proves the validity of the conjecture made by Frank Rosenblatt 70 years ago about the potential capabilities of AI, especially in the realm of artificial neural networks. This paper also gives the answer to the two widely discussed fundamental questions: 1) whether AI could have potentials of discovering new principles in nature; 2) whether error backpropagation (BP) algorithm commonly and efficiently used in tuning parameters in AI applications is also adopted in the brain. Intelligence is just one of fortuitous but sophisticated creations of the nature which has not been fully discovered. Like mathematics and physics, with no restrictions artificial intelligence would lead to a new subject with its self-contained systems and principles. We anticipate that this paper opens new doors for 1) AI twins and other AI techniques to be used in cellular level of efficient neuroscience dynamic analysis, functioning analysis of the brain and brain illness solutions; 2) new worldwide collaborative scheme for interdisciplinary teams concurrently working on and modelling different types of neurons and synapses and different level of functioning subsystems of the brain with AI techniques; 3) development of low energy of AI techniques with the aid of fundamental neuroscience properties; and 4) new controllable, explainable and safe AI techniques with reasoning capabilities of discovering principles in nature.
-
9. ShaderNN: A Lightweight and Efficient Inference Engine for Real-time Applications on Mobile GPUs.
PMID:日期:2025-01-01Inference using deep neural networks on mobile devices has been an active area of research in recent years. The design of a deep learning inference framework targeted for mobile devices needs to consider various factors, such as the limited computational capacity of the devices, low power budget, varied memory access methods, and I/O bus bandwidth governed by the underlying processor's architecture. Furthermore, integrating an inference framework with time-sensitive applications - such as games and video-based software to perform tasks like ray tracing denoising and video processing - introduces the need to minimize data movement between processors and increase data locality in the target processor. In this paper, we propose Shader Neural Network (ShaderNN), an OpenGL-based, fast, and power-efficient inference framework designed for mobile devices to address these challenges. Our contributions include the following: (1) the texture-based input/output provides an efficient, zero-copy integration with real-time graphics pipelines or image processing applications, thereby saving expensive data transfers between CPU and GPU, which are unavoidable in most existing inference engines; (2) we are the first to leverage fragment shaders based on the OpenGL backend in neural network inference operators, which has an advantage in deploying parametrically small neural network models; (3) a hybrid implementation of the compute shader and fragment shader is proposed that enables layer-level shader selection to boost performance; and (4) we utilize OpenGL features - such as normalization, interpolation and texture padding - to improve performance. Experiments illustrate the favorable performance of ShaderNN over other popular on-device deep learning frameworks such as TensorFlow-Lite on the latest mobile devices powered by Qualcomm and MediaTek chips. A case study further demonstrates the usability and integration of the ShaderNN framework with a media processing Android application seamlessly. ShaderNN is available open source at Github (https://github.com/inferenceengine/shadernn).
-
10. Comparing multi-class classifier performance by multi-class ROC analysis: A nonparametric approach.
PMID:日期:2024-05-28The area under the Receiver Operating Characteristic (ROC) curve (AUC) is a standard metric for quantifying and comparing binary classifiers. Real world applications often require classification into multiple (more than two) classes. For multi-class classifiers that produce class membership scores, a popular multi-class AUC (MAUC) variant is to average the pairwise AUC values [1]. Due to the complicated correlation patterns, the variance of MAUC is often estimated numerically using resampling techniques. This work is a generalization of DeLong's nonparameteric approach for binary AUC analysis [2] to MAUC. We first derive the closed-form expression of the covariance matrix of the pairwise AUCs within a single MAUC. Then by dropping higher order terms, we obtain an approximate covariance matrix with a compact, matrix factorization form, which then serves as the basis for variance estimation of a single MAUC. We further extend this approach to estimate the covariance of correlated MAUCs that arise from multiple competing classifiers. For the special case of binary correlated AUCs, our results coincide with that of DeLong. Our numerical studies confirm the accuracy of the variance and covariance estimates. We provide the source code of the proposed covariance estimation of correlated MAUCs on GitHub (https://tinyurl.com/euj6wvsz) for its easy adoption by machine learning and statistical analysis packages to quantify and compare multi-class classifiers.