Data & Analytics

Digital quantum reservoir computing (QRC) framework for time series forecasting on near-term quantum devices. Uses parametrized four-qubit reservoirs with partial measurement and reset, encoding temporal data in rotation angles. Training restricted to classical Ridge-regression readout. Use when: quantum reservoir computing, time series forecasting, near-term quantum devices, ATM cash demand prediction, quantum ML for financial data.

**arXiv ID:** 2101.02153 **Authors:** Benedek Rozemberczki, Rik Sarkar **Published:** 2021-01-06T17:40:23Z **Abstract:** What is the value of an individual model in an ensemble of binary classifiers? We answer this question by introducing a class of transferable utility cooperative games called \textit{ensemble games}. In machine learning ensembles, pre-trained models cooperate to make classification decisions. To quantify the importance of models in these ensemble games, we define \textit{Tr...

Energy-first neural architecture design framework based on biological principles. Systematic validation across vision, text, neuromorphic, and physiological datasets with 2,203 experiments. Activation: energy-first, neural architecture, biological principles, energy-regularized, lambda sweep.

Canonical quantization methodology for constructing quantum neuron models from classical Hamiltonians — a principled framework for quantum machine learning primitives

**arXiv ID:** 2003.06513 **Authors:** Yifan Gong, Zheng Zhan, Zhengang Li, Wei Niu, Xiaolong Ma, Wenhao Wang, Bin Ren, Caiwen Ding, Xue Lin, Xiaolin Xu, Yanzhi Wang **Published:** 2020-03-13T23:52:03Z **Abstract:** Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices. However, previous pruning methods mainly focus on reducing the model size and/or improving performance without considering the privacy of ...

Methodology for auditing and distilling deep reinforcement learning hedging policies into interpretable symbolic formulas. Includes framework for analyzing delta corrections relative to Black-Scholes, symbolic regression distillation, and regime fragility stress-testing. Use when analyzing neural hedging strategies, quantitative risk management, options hedging with RL, or making black-box financial AI auditable.

深度连续局部学习方法论（DECOLLE）。在脉冲神经网络中实现局部突触可塑性规则，通过合成梯度实现端到端训练。适用于事件驱动视觉、神经形态计算、在线学习、脉冲神经网络研究。触发词：DECOLLE、脉冲神经网络、突触可塑性、局部学习、神经形态计算、在线学习、spiking neural network、synaptic plasticity、neuromorphic computing。

Decentralized Momentum Tracking with Biased Gradients (Biased-DMT) for large-scale distributed optimization. Handles communication compression and data heterogeneity in decentralized learning. Use for: decentralized optimization, federated learning, distributed ML, gradient compression, biased gradients. Activation: decentralized optimization, biased gradients, momentum tracking, distributed learning, federated learning, gradient compression.

Copula-based Markov chain methodology for offline change-point estimation in financial time series with Weibull marginals. Handles nonlinear serial dependence in nonnegative financial data (volumes, durations, volatility). Use when analyzing regime changes in financial data, detecting structural breaks in trading volumes or volatility, modeling time series with copula-based dependence, or working with Weibull-distributed financial quantities.

CNN + Adversarial Autoencoder (AAE) for EEG signal classification — from raw EEG to image representations, latent-space regularization, and robust brain-computer interface (BCI) decoding.

Minimum-Distortion Embedding (MDE) framework for analyzing evolving neuronal network dynamics. Use when dimensionality-reducing high-dimensional spiking activity, analyzing network development trajectories, or comparing stimulation effects in neuronal cultures.

Minimum-Distortion Embedding (MDE) framework for analyzing evolving neuronal network dynamics. Use when dimensionality-reducing high-dimensional spiking activity, analyzing network development trajectories, or comparing stimulation effects in neuronal cultures.

Matrix spectral functions methodology for data appraisal, unifying neural scaling laws and Vendi Score. Shows both are submodular, with Vendi Score as a special case. Introduces secular-equation-based updates achieving 35,000x speedup for Vendi optimization. Reveals facility location outperforms Vendi Score for subset selection. Use when: data selection, dataset valuation, Vendi Score optimization, submodular data appraisal, neural scaling laws, matrix spectral functions, training subset sele...

BCI-sift (BCI Systematic and Interpretable Feature Tuning) methodology for automated feature selection in Brain-Computer Interface applications. Integrates advanced optimization algorithms (scikit-learn compatible) to identify informative neural features across electrode, temporal, and frequency dimensions from HD ECoG and other BCI modalities. Activates on BCI feature selection, ECoG decoding optimization, neural feature tuning, automated BCI ML pipeline, brain-computer interface classificat...

Continuous-variable quantum neural networks (CV-QCNN) for biomedical image classification methodology. Uses photonic circuit simulation with Gaussian gates (displacement, squeezing, rotation, beamsplitters) to emulate convolutional behavior for medical imaging tasks. Activation: continuous variable quantum, CV quantum neural network, photonic quantum imaging, biomedical image classification, CV-QCNN, MedMNIST quantum, quantum medical imaging, photonic circuit simulation, Gaussian gate convolu...

Cross-scale spatially-aware generative modeling for transcriptomic programs underlying neurodegenerative brain organization. Variational framework linking gene expression to cortical degeneration with graph-based spatial smoothness. Activation: spatially-aware generative, transcriptomic neurodegeneration, cross-scale brain modeling, cortical thinning prediction, gene-expression degeneration.

Measuring cross-modal neural network convergence using single-stimulus intra-modal dispersion. Generalized Procrustes Algorithm for quantifying how stimuli with low intra-modal dispersion elicit higher cross-modal alignment. Activation triggers: cross-modal convergence, neural network alignment, vision-language alignment, representational similarity.

Statistical methodology for analyzing O(1) coupling expectations in quantum field theories. Quantifies the spread (ratio of largest to smallest dimensionless couplings) and derives closed-form probability distributions for coupling ratios. Use when: analyzing naturalness in particle physics, studying coupling constant distributions, computing probability bounds for hierarchies in QFT, or applying statistical reasoning to fundamental physics parameters. Activates on keywords: O(1) couplings, c...

CORE (Confounding Robustness Enhancement) framework for out-of-distribution generalization in brain network analysis. Addresses site effects and covariate confounding via causal decoupling. Use when: building cross-site classifiers, dealing with scanner/site bias, handling spurious correlations in neuroimaging data, conducting multi-center studies, applying graph neural networks to brain connectivity with domain shifts.

Convex Hybrid Modeling methodology using operator theory for process control and systems engineering. Formulates convex learning problems that combine model interpretability with system identification efficiency. Covers three settings: (1) regularization around a reference model, (2) restriction on interpretable subspaces, (3) kernel-based mixture models on interpretable manifolds. Use when: building interpretable control models, combining physics-based and data-driven modeling, designing hyb...

DBNs spontaneously organize representations by class without supervision.

Framework for analyzing convergent evolution in neural network weight structures during training. Uses matching-based comparison with permutation-invariant features and Hungarian matching to align hidden neurons, then applies structural distance metrics to identify task-specific attractors in weight space.

Systematic methodology for compiling molecular ultrastructure into neural dynamics - bridging microscopic brain structure to computational function. Activation: ultrastructure compiler, molecular neural dynamics, connectome to function, structural biology, neural compilation.

Tsodyks-Markram短时程突触可塑性的混沌动力学。研究确定性TM模型中Shilnikov同宿分岔导致混沌行为的路径，揭示网络动力学不可预测性和对初始条件的敏感性。适用于计算神经科学、突触可塑性建模、混沌动力学分析。触发词：短时程突触可塑性、Tsodyks-Markram模型、Shilnikov分岔、混沌动力学、short-term synaptic plasticity、Tsodyks-Markram model、Shilnikov homoclinic bifurcation、chaotic dynamics。