Data & Analytics

**arXiv ID:** 2407.11038 **Authors:** Dianhui Wang, Gang Dang **Published:** 2024-07-06T01:40:31Z **Abstract:** This paper presents a novel neuro-fuzzy model, termed fuzzy recurrent stochastic configuration networks (F-RSCNs), for industrial data analytics. Unlike the original recurrent stochastic configuration network (RSCN), the proposed F-RSCN is constructed by multiple sub-reservoirs, and each sub-reservoir is associated with a Takagi-Sugeno-Kang (TSK) fuzzy rule. Through this hybrid fram...

**arXiv ID:** 2605.21903 **Authors:** Joseph Nyangon **Published:** 2026-05-21T02:25:05Z **Abstract:** The integration of machine learning with domain-specific physics is transforming the design, monitoring, and control of electricity systems, where data scarcity, limited interpretability, and the need to enforce physical laws constrain purely data-driven models. Physics-informed machine learning (PIML) addresses these limitations by embedding governing equations directly into the learning pr...

**arXiv ID:** 2105.14506 **Authors:** Jivitesh Sharma, Rohan Yadav, Ole-Christoffer Granmo, Lei Jiao **Published:** 2021-05-30T11:29:49Z **Abstract:** In this article, we introduce a novel variant of the Tsetlin machine (TM) that randomly drops clauses, the key learning elements of a TM. In effect, TM with drop clause ignores a random selection of the clauses in each epoch, selected according to a predefined probability. In this way, additional stochasticity is introduced in the learning phas...

**arXiv ID:** 2504.19027 **Authors:** Volkan Bakir, Polat Goktas, Sureyya Akyuz **Published:** 2025-04-26T21:22:44Z **Abstract:** Explainable artificial intelligence (XAI) has become increasingly important in decision-critical domains such as healthcare, finance, and law. Counterfactual (CF) explanations, a key approach in XAI, provide users with actionable insights by suggesting minimal modifications to input features that lead to different model outcomes. Despite significant advancements, e...

Coarse feedback for human-aligned visual representations. Use when: studying how supervisory signal granularity affects brain alignment in neural networks, designing brain-aligned vision models with minimal supervision, comparing coarse vs fine-grained training objectives, deriving coarse category labels from pretrained embeddings (PCA-based splits), representational similarity analysis (RSA) of neural/behavioral alignment, building AI systems aligned with human perception, or investigating w...

Large-scale AI benchmarking methodology for cancer detection models. Evaluates tumor-detection AI across tumor size, location, demographic subgroups, and imaging protocols using 85,355 CT scans and 12 models. Use when: benchmarking medical AI models, evaluating cancer detection systems, assessing subgroup fairness in healthcare AI, analyzing CT scan AI performance, building robust tumor detection pipelines.

MS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classification (arXiv: 2608.05196)

**arXiv ID:** 2506.03588 **Authors:** Hiroki Shiraishi, Hisao Ishibuchi, Masaya Nakata **Published:** 2025-06-04T05:38:49Z **Abstract:** The decision-making process significantly influences the predictions of machine learning models. This is especially important in rule-based systems such as Learning Fuzzy-Classifier Systems (LFCSs) where the selection and application of rules directly determine prediction accuracy and reliability. LFCSs combine evolutionary algorithms with supervised learnin...

Wavelet-Enhanced Mixture-of-Experts (WaveMoE) foundation model for time series forecasting. Use when building time series prediction models, incorporating frequency-domain information, or designing MoE architectures for temporal data.

Systematic RSA comparison showing untrained CNNs match backpropagation-trained CNNs at V1 visual cortex. Untrained random-weights CNN (rho=0.076) exceeds backprop (rho=0.034) at V1/V2 (p<0.001). STDP achieves highest V1 alignment among trained rules (rho=0.064). Four learning rules (BP, FA, PC, STDP) compared against human fMRI from THINGS-fMRI dataset (720 stimuli, 3 subjects).

Systematic RSA comparison showing untrained CNNs match backpropagation at V1 alignment with human fMRI. Evaluates BP, FA, PC, and STDP learning rules against THINGS-fMRI dataset using 720 stimuli across 3 subjects. Use when studying brain-model alignment, comparing learning rules, or analyzing visual cortex representations via Representational Similarity Analysis.

Systematic RSA comparison showing untrained CNNs match backpropagation-trained CNNs at V1 visual cortex. Trigger words: untrained CNN, backpropagation, RSA, V1, representational similarity

Systematic RSA comparison showing untrained CNNs match backpropagation-trained networks at V1 visual cortex, revealing architecture's dominant role over learning rules in neural alignment. Activation triggers: untrained cnn, backpropagation, v1, rsa, representational similarity, learning rules, architecture-driven.

Systematic RSA comparison showing untrained CNNs match backpropagation-trained CNNs in V1 visual cortex alignment. Large-scale fMRI analysis reveals that random feature detectors can capture V1 representational structure. Keywords: untrained CNN, V1 cortex, backpropagation, RSA, representational similarity, visual cortex, fMRI.

Formalizes how attractor networks emerge from the free energy principle applied to universal partitioning of random dynamical systems. Results in self-orthogonalizing attractor representations, biologically plausible multi-level Bayesian active inference. Use when: studying attractor dynamics in neural networks, free energy principle applications, Bayesian active inference models, biologically plausible learning, Boltzmann Machine variants, self-organizing neural dynamics. Triggered by: free ...

RNN权重初始化、解的多样性与性能退化分析框架。研究不同初始化如何收敛到不同动力学解，分析网络规模、时间间隔、连接损伤对性能的优雅退化影响。适用于计算神经科学、RNN模型分析、脑皮层建模。触发词：RNN初始化、解多样性、性能退化、网络鲁棒性、优雅退化、weight initialization、degradation analysis、RNN dynamics、graceful degradation。

Parallel multi-circuit quantum feature fusion methodology for medical image classification. Use when: (1) building hybrid quantum-classical CNN architectures for biomedical image classification, (2) comparing quantum vs classical models with statistical rigor (Wilcoxon signed-rank test, Cohen's d effect size), (3) designing parallel quantum encoding circuits (amplitude + angle encoding simultaneously), (4) parameter-matched fairness evaluation for QML vs classical baselines. Covers QCNN archi...

Preisach Attention Layer (PAL) — a novel sequence modeling architecture that replaces softmax attention with the classical Preisach hysteresis operator from mathematical physics. Uses binary relay operators with learned thresholds and a stack of local extrema as internal state. Achieves Turing-completeness at O(1) depth via two-stack PDA simulation. Activation: attention, hysteresis, sequence modeling, episodic memory, transformer alternative, rate-independent computation

Physics-informed Neural Networks (PINNs) for biomedical modeling and simulation. Use when working on physics-guided neural network approaches for hemodynamics, cardiovascular modeling, blood flow prediction, or inverse medical physics problems. Combines physical principles with neural networks for personalized medical predictions with minimal data requirements.

Linear equivalence of nonlinear recurrent neural networks using two-site cavity method. Shows covariance matrix of large nonlinear RNNs takes same form as linear networks with mean-field order parameters. Activation: nonlinear RNN, linear equivalence, cavity method, mean-field analysis, covariance matrix.

Analytical solution for large nonlinear recurrent neural networks at fixed connectivity. Calculates moments and response functions without synaptic weight averaging, linking connectivity to spontaneous activity and perturbation response. Trigger words: nonlinear RNN, fixed connectivity, moments, response functions, large N limit.

Multisensory learning methodology that recruits visual neurons into olfactory memory engrams through cross-modal binding. Using Drosophila model to study how combining sensory modalities expands memory engrams and improves recall performance. Activation triggers: multisensory learning, memory engram, cross-modal binding, neural circuits, sensory integration.

Meta-Learning Biologically Plausible Plasticity Rules

Framework for analyzing learning dynamics in low-rank RNNs via overlap space decomposition. Distinguishes loss-visible overlaps (determine activity/output/loss) from loss-invisible overlaps (encode training history). Enables understanding of why functionally equivalent networks learn differently. Activation: low-rank RNN learning, RNN overlap space, loss-visible invisible, RNN gradient descent dynamics, RNN learning theory, Ger Barak RNN.