Data & Analytics

**arXiv ID:** 2604.13081 **Authors:** Talha Ruzgar Akkus, Suayp Talha Kocabay, Kamer Ali Yuksel, Hassan Sawaf **Published:** 2026-03-28T23:11:21Z **Abstract:** The Forward-Forward (FF) algorithm trains networks layer-by-layer using a local "goodness function," yet sum-of-squares (SoS) has remained the only choice studied. We systematically explore the goodness-function design space and identify a unifying principle: the goodness function must be sensitive to the shape of neural activity, not ...

Secretary problem optimal stopping thresholds are exactly the convergents of 1/e via continued fractions. If p/q is a continued fraction convergent of 1/e with q at least 3, then for q applicants the optimal number to initially reject is p. Connects optimal stopping theory, continued fractions, and the mathematical constant e. Use when: optimal stopping problems, secretary problem analysis, continued fraction applications, 1/e thresholds, decision theory, sequential selection.

Supervised Deep Multimodal Matrix Factorization (SD3MF) methodology for interpretable brain network analysis. Generalizes SNMTF from unsupervised single-graph clustering to supervised prediction over populations of multimodal graphs. Learns deep hierarchical factorizations with shared latent representations that align subjects across modalities via encoder-decoder formulation. Use when: analyzing multimodal connectome data, building interpretable brain network classifiers, performing supervis...

SIMON: Saliency-aware Integrative Multi-view Object-centric Neural Decoding for zero-shot EEG-to-image retrieval. Uses foreground segmentation, saliency prediction, Saliency-Aware Sampling (SAS), and foveated multi-view integration to overcome center-bias limitations in EEG-to-image retrieval. Trigger words: saliency-aware EEG decoding, SIMON, EEG-to-image retrieval, foveated view, multi-view neural decoding, Saliency-Aware Sampling, object-centric neural decoding, zero-shot EEG image, THINGS...

SAE 最优性结构理论 - 解释 Sparse Autoencoders 如何从最优性条件提取可解释特征。涵盖层次分裂与吸收、残差结构、密集对立特征等现象的理论基础。

Novel coupling methodology for Rulkov neural maps preserving chaos and generating strange attractors

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。

Paper analysis: Identifying structural design principles shaping computational abilities of recurrent neural networks. Demonstrates that local 2- and 3-cycles in connectivity strongly enhance computational ability of RNNs, and that adding sparse biologically-inspired interneurons dramatically increases capacity. Complete catalogs of network-function performance reveal most networks fail at most functions. Source: arXiv:2606.23874 (q-bio.NC, cs.NE), 2026-06-22. Activation keywords: RNN structu...

Bures-Wasserstein metric-based Riemannian self-attention network for robust EEG decoding

**arXiv ID:** 1809.03864 **Authors:** Ramin M. Hasani, Alexander Amini, Mathias Lechner, Felix Naser, Radu Grosu, Daniela Rus **Published:** 2018-09-11T13:27:36Z **Abstract:** In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level. We propose a systematic pipeline for interpreting individual hidden state dynamics within the network using response characterization methods. The ranked c...

Associative presynaptic short-term plasticity via information-theoretic learning rules maximizing stimulus information under resource constraints

Renormalization group (RG) framework for analyzing scaling laws and criticality in brain activity. Connects 1/f noise, neuronal avalanches, and coarse-grained descriptions through RG theory. Activates: renormalization brain, scaling law neural activity, 1/f noise brain, neuronal avalanche scaling, coarse-graining neural dynamics, RG criticality brain, power law neural scaling.

Recurrent Divisive Normalization Network (RDNN) framework for continuous working memory with low-rank slow manifolds. Provides implementation guidance for stable continuous manifold learning in RNNs using divisive normalization to prevent state space shattering into discretized point attractors. Use when modeling continuous working memory, neural manifolds, or stable RNN dynamics.

Quantum cloud platform authentication framework using multi-dimensional quantum fingerprints from raw measurement data. Constructs Mahalanobis-based fingerprints with drift early warning and adversarial detection to verify which physical device executes workloads, preventing hardware substitution attacks. Activation: quantum authentication, cloud verification, hardware fingerprinting, quantum cloud, device authentication, Mahalanobis distance, drift detection, adversarial detection, raw-curve

Random Riemann Zeta Function integral means spectrum methodology — connects random vertical shifts of zeta-function to Kraetzer's universal integral means spectrum conjecture via Gaussian multiplicative chaos (GMC). Use for: analytic number theory, random zeta functions, GMC, conformal mapping, multifractal analysis. arXiv: 2603.26507.

Quantum Viterbi decoding methodology for hidden quantum Markov models (HQMMs). Extends classical Viterbi algorithm to quantum sequential decision-making with proven advantage over classical diagonal strategies.

Quantum-inspired evolutionary optimization for non-convex ML landscapes using superposition-inspired probabilistic encoding and simulated tunneling to escape local optima. Use when classical optimizers (ADAM, GA, DE) get stuck in local minima on sparse signal recovery, robust regression, or any non-convex objective. Triggers: non-convex optimization, local optima escape, quantum tunneling optimizer, sparse signal recovery, robust regression, quantum evolutionary algorithm, superposition-inspi...

Quantum algorithms for graph triangle cut sparsification methodology. Uses quantum walks and Grover search to list triangles faster than classical bounds, enabling efficient construction of ε-sparsifiers for large-scale network analysis.

Exact framework for computing heat, energy, and particle transport statistics in quadratic quantum systems coupled to Gaussian reservoirs — combines full counting statistics with non-Markovian master equations. Use when: analyzing quantum transport in mesoscopic systems, computing full counting statistics for particle/heat currents, studying non-Markovian open quantum systems, evaluating transport between quantum reservoirs, or modeling quantum thermodynamic engines.

Qlustering: Unsupervised clustering via steady-state quantum transport in GKSL-governed quantum networks. Data encoded as input states, cluster assignments inferred from terminal output currents. Use when: quantum machine learning, unsupervised quantum clustering, GKSL master equation applications, open quantum network learning, quantum data clustering, or algorithm-hardware co-design for quantum ML.

Quantum algorithms for topological data analysis (TDA) - persistent Betti numbers, simplicial complexes, Vietoris-Rips topology, high-dimensional feature extraction. Use when analyzing quantum approaches to TDA, persistent homology, Betti number estimation, topological quantum computing, or geometry-informed quantum algorithms.

Quantum and classical algorithms for topological data analysis (TDA) including persistent Betti numbers computation, simplicial complex construction, and persistence diagram interpretation. Use when analyzing topological features of data, persistent homology, Betti numbers, simplicial complexes, or topological data analysis. Triggers: TDA, 拓扑数据分析, Betti numbers, Betti数, persistent homology, 持久同调, simplicial complex, 单纯复形, quantum TDA, quantum topology.

Quantum Time Lower Bounds by Permutation Invariance. Use when analyzing quantum algorithms, complexity bounds, quantum ML architectures, or quantum error correction involving mathematical analysis and statistical methods.

Local tensor-train surrogates methodology for quantum machine learning models. Constructs fast, cheap, provably accurate classical surrogates of fully trained QML models within local patches of input data space. Combines Taylor polynomial approximation with tensor-train representation via empirical risk minimization. Use when implementing efficient quantum ML inference acceleration, tensor-train approximation of quantum circuits, or local surrogate modeling for QML.