Data & Analytics

Just EEG Transformer (JET) — generative EEG framework using conditional flow matching to model neural signals as continuous trajectories, preserving spectral structure, temporal stationarity, and signal statistics. ICML 2026. Reduces TS-FID by >40% on large-scale benchmarks. arXiv:2605.21280

Jeffreys Flow framework for robust Boltzmann generators and rare event sampling. Addresses mode collapse in multi-modal distributions using Jeffreys divergence + Parallel Tempering distillation. Use when: sampling rough energy landscapes, Boltzmann generators, rare events, quantum thermal states, path integral Monte Carlo, avoiding KL divergence mode collapse.

First-passage-time analysis of inter-spike interval (ISI) statistics for excitatory-inhibitory (EI) integrate-and-fire neurons with depolarizing and hyperpolarizing adaptive thresholds. Use when studying stochastic neuronal firing, ISI variability, adaptive threshold mechanisms, or EI balance effects on spike-time statistics.

Stochastic Cortical Self-Reconstruction (SCSR) framework for personalized mapping of gray matter atrophy in neurodegenerative disorders. Enables individualized healthy reference estimation directly from observed cortical thickness at vertex level, allowing detection of subtle subject-specific deviations. Evaluates generalization and transferability across populations (UK Biobank to Chinese dataset) with multiple training strategies and reconstruction backbones.

Quantum data mining methodologies for information science — frequent itemset mining, quantum pattern discovery, and quantum-enhanced analytics on NISQ devices.

Tensor-based framework for higher-order Markov chains with memory on hypergraphs. Use when modeling complex systems with group interactions, memory effects, non-pairwise connections, or analyzing higher-order networks. Keywords: hypergraph, Markov chains, memory, tensor, higher-order networks, complex systems, random walks.

Hyperbolic Graph Convolutional Network (Brain-HGCN) for brain functional network analysis using Lorentz model and signed aggregation for excitatory/inhibitory connections. Activation triggers: hyperbolic GNN, brain network, fMRI analysis, geometric deep learning, Lorentz model.

HyFuHAD: Hybrid Quantum-Fuzzy Hyperspectral Anomaly Detection methodology. Combines Einstein fuzzy computing for classical inference with lightweight quantum defuzzifier for final detection. Uses multi-criteria decision framework with morphological, geometrical, and statistical membership functions. Use when: hyperspectral image anomaly detection, quantum neural network for remote sensing, fuzzy computing for image processing, Einstein fuzzy operations, or hybrid quantum-classical image analy...

Hybrid quantum-classical neural network methodology for medical image classification, particularly thermographic breast cancer detection. Integrates quantum neural network layers with classical CNN backbones to enhance pattern recognition in complex medical imaging data. Use when: (1) hybrid quantum-classical architectures for medical diagnosis, (2) quantum-enhanced image classification in healthcare, (3) thermographic/thermal image analysis with quantum methods, (4) quanvolutional networks f...

Design and evaluate hybrid quantum-classical machine learning pipelines for medical image classification and diagnosis. Covers HQNN, HQCNN, CV-QNN architectures, federated learning with tensor-network frontends, and quantum-enhanced feature extraction for healthcare applications. Use when: (1) building quantum-enhanced medical diagnosis systems, (2) designing hybrid quantum-classical ML pipelines for healthcare, (3) evaluating QML for medical imaging, (4) federated medical learning with quant...

Hybrid biophysical neuron modeling methodology combining conductance-based models with neural ODEs. Captures unknown ion channel kinetics while preserving mechanistic interpretability. Enables single-compartment reduction of multi-compartment models.

Hybrid Quantum-Classical Neural Network (HQNN) methodology for medical image classification, specifically blood cell classification. Combines pre-trained classical backbone (ResNet-50) with variational quantum circuit for enhanced feature representation. Use when: (1) medical image classification with limited data, (2) hybrid quantum-classical ML pipeline design, (3) comparing quantum vs classical feature transformations, (4) NISQ-era quantum advantage in medical imaging. Activation: HQNN, hy...

Statistical-mechanical theory of dreaming in multidirectional associative memories using DLAM architecture. Use when: (1) implementing energy-based models with dreaming capabilities; (2) designing multi-layer Hebbian architectures; (3) analyzing pattern disentanglement in neural networks; (4) studying statistical mechanics of neural memory; (5) developing heteroassociative memory systems. Trigger words: Hopfield dreaming, DLAM, associative memory, energy-based models, pattern disentanglement.

Homology-based Morphometry (HBM) methodology for analyzing brain atrophy using persistent homology. Two complementary pipelines for quantifying multiscale geometric features of structural T1-weighted MRI scans: Pipeline 1 for regional thinning via Euclidean distance transform, Pipeline 2 for structural similarity via α-filtrations. Use for Alzheimer's disease detection, longitudinal brain change tracking, and topological biomarker extraction. Keywords: brain atrophy, persistent homology, TDA,...

Homology-based morphometry methods for analyzing brain atrophy using topological data analysis. Activation triggers: homology morphometry, brain atrophy, topological neuroimaging, persistent homology brain, TDA neuroimaging

Extracting interpretable higher-order topological features across multiple scales for Alzheimer's Disease classification using persistent homology. Captures connected components, cycles, and cavities from fMRI brain networks. Activation: higher-order topology, Alzheimer classification, persistent homology, brain network topology, topological features.

Methodology for extracting high-order functional brain network structures beyond pairwise connections under global constraints. Addresses theoretical limitations of pairwise FBN modeling. Activation: higher-order brain networks, beyond pairwise, global constraints, FBN limitations.

Higher-order brain network analysis using topological signal processing. Captures circulatory and multi-node interactions beyond pairwise graph models.. Activation: higher-order networks, topological signal processing, brain connectomics.

Parallelized Hierarchical Connectome (PHC) framework that upgrades temporal State-Space Models into spatiotemporal recurrent networks for brain connectivity modeling.. Activation: hierarchical connectome, state-space models, spatiotemporal.

Robust volatility updates for Hierarchical Gaussian Filtering (HGF). Improves stability and convergence of uncertainty estimation in perceptual inference. Activation: hierarchical gaussian filter, volatility update, perceptual inference, active inference, uncertainty estimation.

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...

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.

**arXiv ID:** 1605.07156 **Authors:** Laura Deming, Sasha Targ, Nate Sauder, Diogo Almeida, Chun Jimmie Ye **Published:** 2016-05-23T19:43:08Z **Abstract:** Each human genome is a 3 billion base pair set of encoding instructions. Decoding the genome using deep learning fundamentally differs from most tasks, as we do not know the full structure of the data and therefore cannot design architectures to suit it. As such, architectures that fit the structure of genomics should be learned not presc...

Foundation models for discovering robust biomarkers of neurological disorders from dynamic functional connectivity. Use when: building neurological biomarker discovery pipelines, applying foundation models to fMRI/EEG data, analyzing dynamic functional connectivity for disease detection, developing robust cross-subject biomarkers. Triggers: brain biomarker foundation model, dynamic functional connectivity biomarker, neurological disorder detection, robust biomarker discovery, fMRI foundation ...