Data & Analytics

Extended STDP learning rule for simultaneously learning synaptic connection strengths and delays, validated on unsupervised SNN classification tasks with superior performance over delay-free STDP.

Statistical interpretation framework unifying algebraic quantum mechanics and quantum probability theory — links observable algebras to measurement statistics for foundations of quantum physics. Use when: analyzing measurement procedures statistically, bridging algebraic and probabilistic formulations of quantum mechanics, studying quantum observables as statistical functionals, or developing measurement-based interpretations of quantum theory.

Analysis of Neural Tangent Kernel (NTK) collapse near dynamical bifurcations in state-space models. Studies how the NTK spectrum degrades as recurrent networks approach critical transitions. Activation: NTK collapse, bifurcation analysis, state-space NTK, critical transitions neural networks, dynamical systems deep learning.

STARS (Spike Tail-Aware Relational Synthesis) - plug-and-play method for ANN-to-SNN Data-Free Knowledge Distillation (DFKD). Augments BN-guided synthesis with Relational Consistency Alignment and Tail-Aware Regularization. Achieves up to 4.6% improvement on CIFAR-10 and 6.7% on CIFAR-100. Activation: SNN knowledge distillation, data-free distillation, ANN-to-SNN conversion, tail-aware regularization, relational consistency, spike threshold dynamics, 无数据蒸馏, 跨模态蒸馏.

SpikingMoE — spike-driven Transformer with LGN-inspired Mixture-of-Experts (MoE) for dynamic computation in SNNs

Spiking Transformers Theory - Effective Dimension analysis framework for Spiking Transformers (S-ViT). Provides theoretical bounds on generalization and robustness using VC dimension, Rademacher complexity, and effective dimension metrics. Use when analyzing Spiking Transformer architectures, evaluating SNN generalization bounds, comparing S-ViT with ANN-ViT capacity, or studying temporal coding effects on model complexity. Triggers: spiking transformer, effective dimension, S-ViT, spiking Vi...

SPATE methodology for spiking-phase adaptive temporal encoding in quantum machine learning. Converts real-valued data into leaky integrate-and-fire spike trains and maps spike statistics to quantum rotations with temporal qubits. Use when: quantum ML encoding, spike-driven temporal encoding, quantum feature preparation, temporal qubits, QML pipeline enhancement.

SPATE methodology for quantum machine learning — spiking-phase adaptive temporal encoding. Converts real-valued features into leaky integrate-and-fire spike trains and maps spike statistics to quantum rotations, augmented with temporal qubits via controlled phase operations. Use when: (1) designing QML pipelines for temporal data, (2) encoding time-series/tabular data into quantum feature spaces, (3) comparing spike-based vs angle/amplitude encoding quality, (4) building hybrid quantum neural...

Differential equation analysis of SNN dynamics. Translates discrete spiking models into continuous ODE/PDE formulations for stability analysis, bifurcation study, and dynamical systems characterization. Activation: SNN differential equations, spiking dynamics analysis, ODE neuron model, bifurcation SNN, continuous-time spiking, dynamical systems neuroscience

SpikeProphecy: First large-scale benchmark for causal, autoregressive neural population spike-count forecasting. Introduces population metric decomposition (temporal fidelity, spatial pattern accuracy, magnitude-invariant alignment) on 105 Neuropixels sessions (~89,800 neurons). arXiv:2605.12992

脉冲时序训练和自发强化神经元集群。研究STDP如何形成共享刺激偏好的强耦合神经元集群，自发动力学期间的脉冲相关性主动强化连接。适用于计算神经科学、STDP学习、神经编码研究。触发词：神经元集群、STDP、脉冲时序、神经编码、自发动力学、neuronal assembly、spike timing、STDP、noise correlation。

Spike Agreement Dependent Plasticity (SADP) - biologically inspired learning rule for SNNs using population-level correlation metrics instead of precise spike timing. Activation triggers: spike agreement, synaptic plasticity, SNN learning, bio-inspired learning, population correlation, neuromorphic learning.

Sparse Mamba Decoder (SMD) for quantum error correction — a defect-centric neural decoder using Mamba state-space model that processes only active detection events (k ≪ d²R) achieving O(k) complexity on surface codes. 95-467x faster than Tesseract near-MLD decoder.

信噪比和样本数量调控神经网络表征对齐的方法论。研究神经网络潜在表征的通用性规律，揭示对齐与数据质量和数量的非平凡依赖关系。适用于表征对齐分析、神经网络可解释性、训练优化。触发词：表征对齐、SNR、样本数量、插值阈值、通用表征。

Spiking Neural Networks with Astrocyte-Like Units - incorporating glial cell dynamics for improved learning, achieving optimal performance at 2:1 astrocyte-to-neuron ratio matching biological estimates. Activation triggers: astrocyte, glial cells, tripartite synapse, SNN learning, liquid state machine, biological realism.

**arXiv ID:** 2410.15318 **Authors:** Tianyi Xu, Patrick Zheng, Shiyan Liu, Sicheng Lyu, Isabeau Prémont-Schwarz **Published:** 2024-10-20T07:20:33Z **Abstract:** Artificial Neural Networks (ANNs) suffer from catastrophic forgetting, where the learning of new tasks causes the catastrophic forgetting of old tasks. Existing Machine Learning (ML) algorithms, including those using Stochastic Gradient Descent (SGD) and Hebbian Learning typically update their weights linearly with experience i.e., ...

Simulatable Processes framework for learning under dependent data with access to a simulator. Recovers PAC-style VC-dimension bounds for arbitrarily complex dependent processes, with regret controlled by time-bounded Kolmogorov complexity. COLT 2026 paper. arXiv: 2606.13576

Complex dynamics in the Sherrington-Kirkpatrick (SK) game methodology — game-theoretic foundation for adaptive learning in disordered many-player systems with random payoff matrices. Generalizes the SK spin-glass model to game theory with random-field bias, grand-canonical abstention, and convergence/volatility phase diagram. Bridges spin-glass neural network theory, reinforcement learning, and game theory. arXiv:2607.02422

Sharma-Mittal entropy framework bridging information theory, black hole thermodynamics, and infrared gravity modifications. Derives modified gravitational force laws from generalized entropy, reproduces MOND-like regime. Activates: sharma-mittal entropy, generalized entropy, emergent gravity, MOND, black hole thermodynamics, information bounds, infrared gravity, entropic gravity

Semiclassical methods connecting quantum statistical mechanics to analytic number theory. Uses trace formula and periodic orbit theory to study integer partitions. Activation: semiclassical, integer partitions, density of states, number theory, periodic orbit, trace formula, Pythagorean triples.

SABER framework for semantic-aligned brain network analysis via multi-scale hypergraphs. Actively integrates LLM-derived semantics into brain network prediction, combining global self-attention, multi-scale hypergraph construction, and decision-level semantic alignment for improved brain disease diagnosis. Use when building brain network classifiers, fMRI/EEG analysis pipelines, or LLM-brain integration systems.

**arXiv ID:** 2211.11491 **Authors:** Zsolt János Viharos, Ágnes Szűcs **Published:** 2022-11-21T14:26:46Z **Abstract:** The paper analyses and serves with a positioning of various error measures applied in neural network training and identifies that there is no best of measure, although there is a set of measures with changing superiorities in different learning situations. An outstanding, remarkable measure called $E_{Exp}$ published by Silva and his research partners represents a research ...

Finite combinatorial analogue of Gödel's incompleteness theorems within Boolean K-SAT. Proves self-referential hardness exhibits physical invariance precluding quantum shortcuts due to necessity of global semantic analysis, and delineates scaling bottleneck for ML on lossy local compression.

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 ...