Data & Analytics

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 ...

Novel approach to dictionary learning on fMRI data that explicitly accounts for individual brain geometry variability using optimal transport (Fused Gromov-Wasserstein distance) with amortized optimization for computational efficiency.

Fermi-Dirac quantization methodology for neural networks — reinterprets classical neurons as parameterized Hamiltonians and replaces variables with quantum operators. BQP-complete for certain decision problems. Use when: designing quantum neural architectures, quantizing activation functions (ReLU, GeLU, sigmoid), building hybrid quantum-classical neural algorithms, analyzing quantum advantage in neural computation, or studying the quantum-classical boundary in machine learning.

FedDOSE federated brain dFC with site decomposition.

Extended predictive coding framework using exponential family distributions beyond Gaussian assumptions. Reveals biological neural network properties: nonlinearity, heterogeneity, biological plausibility. Maintains FEP-PC correspondence up to second cumulant. Derives biologically plausible local plasticity rules from EFD variational free energy. Use when: predictive coding, free energy principle, exponential family, variational inference, biological plausibility, local plasticity rules, neura...

Skill for exploring brain networks using noninvasive electrophysiological measurements (EEG/MEG) based on arXiv:2607.17602v1. Covers forward/inverse problems, source reconstruction, connectivity measures, and analysis pipelines.

**arXiv ID:** 2305.17300 **Authors:** Erik C. Johnson, Brian S. Robinson, Gautam K. Vallabha, Justin Joyce, Jordan K. Matelsky, Raphael Norman-Tenazas, Isaac Western, Marisel Villafañe-Delgado, Martha Cervantes, Michael S. Robinette, Arun V. Reddy, Lindsey Kitchell, Patricia K. Rivlin, Elizabeth P. Reilly, Nathan Drenkow, Matthew J. Roos, I-Jeng Wang, Brock A. Wester, William R. Gray-Roncal, Joan A. Hoffmann **Published:** 2023-05-26T23:04:53Z **Abstract:** Despite the progress in deep learni...

**arXiv ID:** 2604.19761 **Authors:** Kamer Ali Yuksel, Hassan Sawaf **Published:** 2026-03-26T00:07:45Z **Abstract:** Modern machine learning is still largely organized around a single recipe: choose a parameterized model family and optimize its weights. Although highly successful, this paradigm is too narrow for many structured prediction problems, where the main bottleneck is not parameter fitting but discovering what should be computed from the data. Success often depends on identifying t...

**arXiv ID:** 2604.00163 **Authors:** Ferdaus Anam Jibon, Fazlul Hasan Siddiqui, F. Deeba, Gahangir Hossain **Published:** 2026-03-31T19:11:16Z **Abstract:** Epileptic seizures are neurological disorders characterized by abnormal and excessive electrical activity in the brain, resulting in recurrent seizure events. Electroencephalogram (EEG) signals are widely used for seizure diagnosis due to their ability to capture temporal and spatial neural dynamics. While recent deep learning methods ha...

Energy-based dynamical systems framework for neurocomputation, learning, and optimization. Unifies Hopfield networks, Boltzmann machines, modern EBMs, and equilibrium propagation under a single energy landscape formulation. Covers gradient flow dynamics, attractor analysis, contrastive learning, and biologically-plausible learning rules. Activation: energy-based models, EBMs, neural dynamics, Hopfield networks, energy landscape, attractor dynamics, gradient flow, equilibrium propagation, cont...

**arXiv ID:** 2105.00173 **Authors:** Daniel Szelogowski **Published:** 2021-05-01T05:47:15Z **Abstract:** Current computational-emotion research has focused on applying acoustic properties to analyze how emotions are perceived mathematically or used in natural language processing machine learning models. While recent interest has focused on analyzing emotions from the spoken voice, little experimentation has been performed to discover how emotions are recognized in the singing voice -- both ...

Embodied Virtual Reality feedback reshapes neural representations to support continuous 3D motor imagery decoding in brain-computer interfaces. First systematic investigation of embodied VR feedback during real-time 3D virtual limb control. Use when: (1) Designing VR-based BCI systems, (2) Studying motor imagery neural representations, (3) Comparing VR vs screen feedback modalities, (4) Investigating longitudinal BCI training effects. Activation: embodied VR feedback, motor imagery BCI, 3D vi...

Open-source platform cataloguing 791 public neurophysiological datasets (EEG, MEG, iEEG, EMG, fNIRS) with automatic format repair, BIDS compliance, and machine learning integration.

EEG-based tinnitus biomarker identification methodology with cross-dataset generalization. Uses microstate analysis and Koopman operator analysis via DMD to extract robust neural signatures. Focuses on Koopman eigenvalue magnitude for oscillation stability. Applications: clinical diagnostics, cross-platform tinnitus detection. Triggers: tinnitus biomarker, EEG microstate, Koopman EEG, cross-dataset generalization

Deep learning framework for objective consciousness level measurement using multi-dimensional transcranial electrical stimulation (TES) with EEG. Combines TES-evoked brain responses with CNN classification for bedside-awareness assessment. Activation triggers: eeg tes, consciousness measurement, transcranial stimulation, brain state classification, awareness assessment, disorder of consciousness.

Structure-Guided Diffusion Model (SGDM v3) for EEG-based visual cognition reconstruction with enhanced cross-subject generalization. Combines structurally supervised VAE, spatiotemporal EEG encoder with contrastive learning, and ControlNet-guided diffusion for high-fidelity image reconstruction from brain signals.

Skill for analyzing brain networks using noninvasive electrophysiological measurements (EEG/MEG) based on arXiv:2607.17602v1 'Exploring Brain Networks Using Noninvasive Electrophysiological Measurements: Methods and Applications'

EEG-based Hopfield energy landscape analysis for quantifying brain network stability during emotional processing (happy/sad face tasks). Activation: emotion energy landscape, brain stability, happy sad face EEG, Hopfield emotion.

EEG-conditioned framework for reconstructing dynamic fMRI as continuous neural sequences with high spatial fidelity and temporal coherence at cortical-vertex level. Incorporates null-space intermediate-frame reconstruction for handling sampling irregularities.

Gaussian-equivalent process methodology for analyzing nonlinear noise in recurrent neural circuits using Ornstein-Uhlenbeck noise matching and lognormal moment closure. Activation: mean field, nonlinear noise, recurrent networks, OU process.

Dynamic Gated Neuron (DGN) - Biologically plausible gating mechanism for Spiking Neural Networks via dynamic membrane conductance modulation. Enables selective input filtering and adaptive noise suppression. Activation triggers: dynamic gated neuron, DGN, SNN gating, conductance-based SNN, robust spiking neural network, biological gating.

**arXiv ID:** 2206.01829 **Authors:** Yichao Liang, Joshua B. Tenenbaum, Tuan Anh Le, N. Siddharth **Published:** 2022-06-03T21:40:22Z **Abstract:** Learning general-purpose representations from perceptual inputs is a hallmark of human intelligence. For example, people can write out numbers or characters, or even draw doodles, by characterizing these tasks as different instantiations of the same generic underlying process -- compositional arrangements of different forms of pen strokes. Crucia...

Distribution-valued brain connectivity analysis using vector quantiles instead of scalar edge weights. Based on Mhanna, Achard, Petersen (2026, HAL). Use when building brain connectivity graphs from fMRI/EEG, improving connectome classification, or representing higher-order connectivity statistics. Activation: distribution-valued brain connectivity, graph brain representation, fMRI connectome classification, voxel clustering, brain network edges, vector quantile connectivity.

DINA (Dual-Tower Image-Neural Alignment) framework for interpretable contrastive analysis of V1 population activity. Aligns visual stimuli and V1 responses in shared latent space at intermediate feature map level. Activation: DINA, V1 population activity, image-neural alignment, contrastive framework, calcium imaging decoding, visual computation.