Data & Analytics

Electrocardiography (ECG) is one of the most widely used tests for diagnosing cardiovascular disease. Yet several remote clinics still utilize paper ECG printouts for their analysis due to limited con. Based on arXiv:2607.07683.

**arXiv ID:** 1802.03916 **Authors:** Zachary C. Lipton, Yu-Xiang Wang, Alex Smola **Published:** 2018-02-12T07:16:03Z **Abstract:** Faced with distribution shift between training and test set, we wish to detect and quantify the shift, and to correct our classifiers without test set labels. Motivated by medical diagnosis, where diseases (targets) cause symptoms (observations), we focus on label shift, where the label marginal $p(y)$ changes but the conditional $p(x| y)$ does not. We propose B...

Medical imaging classification using cold-atom (neutral-atom) reservoir computing. Combines quantum reservoir computing with auto-encoders and surrogate-driven training for medical image analysis. Use when building quantum-enhanced medical imaging pipelines with reservoir computing.

Convolutional Neural Network framework for detecting gaseous microemboli (GME) during cardiac procedures using transthoracic ultrasound. Activation triggers: emboli detection, cardiac ultrasound, microemboli GME, surgical safety, transcatheter monitoring

RE-CONFIRM framework for validating robustness of biomarkers discovered by brain foundation models from dynamic functional connectivity. Systematic evaluation of internal reliability, external reliability, and validity for clinical biomarkers. Activation: RE-CONFIRM, biomarker validation, brain foundation model, robust biomarkers, dynamic functional connectivity.

**arXiv ID:** 2109.06139 **Authors:** Brendan E. Odigwe, Francis G. Spinale, Homayoun Valafar **Published:** 2021-09-13T17:30:28Z **Abstract:** Heart failure (HF) is a leading cause of morbidity, mortality, and health care costs. Prolonged conduction through the myocardium can occur with HF, and a device-driven approach, termed cardiac resynchronization therapy (CRT), can improve left ventricular (LV) myocardial conduction patterns. While a functional benefit of CRT has been demonstrated, a l...

Adaptive Hybrid Quantum-Classical Feature Fusion methodology for medical image classification. Addresses optimization asymmetries between quantum and classical paradigms using Temperature-Scaled Hybrid Fusion (TSHF) with learnable scalar τ, Dynamic Hybrid Fusion (DHF), and Static Hybrid Fusion (SHF) strategies. Includes implementation scripts (scripts/tshf_fusion.py) for PyTorch. Use when designing hybrid quantum-classical ML pipelines for healthcare/medical imaging, especially when combining...

**arXiv ID:** 2104.08048 **Authors:** Arkadiy Dushatskiy, Tanja Alderliesten, Peter A. N. Bosman **Published:** 2021-04-16T11:51:18Z **Abstract:** We propose a novel surrogate-assisted Evolutionary Algorithm for solving expensive combinatorial optimization problems. We integrate a surrogate model, which is used for fitness value estimation, into a state-of-the-art P3-like variant of the Gene-Pool Optimal Mixing Algorithm (GOMEA) and adapt the resulting algorithm for solving non-binary combina...

Hardware-aware open-source framework for mixed-signal Spiking Neural Network design space exploration. Captures non-ideal analog/digital hardware behavior while supporting system-level exploration for energy-efficient neuromorphic edge computing. Activation: mixed-signal SNN, hardware-aware simulation, design space exploration, neuromorphic edge, non-ideal hardware modeling, SNN accelerator

Hamming quantum kernel for SVMs that avoids exponential concentration problem of fidelity quantum kernel. Uses full measurement statistics rather than single fidelity value. Outperforms fidelity kernel at 15+ qubits and classical Gaussian kernel on synthetic quantum data. Scales to 27 qubits without additional quantum resources. Activation: hamming quantum kernel, quantum SVM, exponential concentration, quantum kernel scalability, fidelity kernel alternative, scalable quantum kernel

Extremely slow scaling of minimal Hamming distance in quantum sampling data. Use when analyzing quantum algorithms, complexity bounds, quantum ML architectures, or quantum error correction involving mathematical analysis and statistical methods.

Hamiltonian-encoded quantum reservoir computing methodology for robust quantum learning on NISQ platforms. Addresses trainability (barren plateaus), hardware efficiency, and information stability through direct Hamiltonian mapping and quantum dynamical evolution.

GTaS Generative Spike Train Model

Methodology for analyzing and mitigating grokking, epoch-wise double descent, and late-stage generalization decay in overparameterized quantum neural networks via weight-norm regularization.

Inter-areal predictive coding for gradient-free continual learning in spiking neural networks. Brain-inspired learning rule using feedback connections to transmit prediction errors without backpropagation. Keywords: gradient-free learning, continual learning, predictive coding, inter-areal, SNN, catastrophic forgetting, bio-inspired.

Geometric Stability of Neural Population Codes methodology - Shesha metric quantifying pairwise distance structure reproducibility across split-half RDMs, dissociable from temporal stability and decoding accuracy. Use when analyzing representational reliability beyond centroid drift, comparing brain regions, or modeling attractor-network mechanisms for RDM consistency. Activation: geometric stability, Shesha, split-half RDM, representational dissimilarity, neural population code, striatum hip...

Geometric Quantum Physics-Informed Neural Network (GQPINN) methodology for solving PDEs with symmetry-aware quantum circuits. Combines geometric quantum machine learning with physics-informed neural networks. Use when solving PDEs with quantum circuits, incorporating symmetry/inductive biases into quantum models, or designing equivariant quantum ansatzes for scientific ML. Activation: geometric quantum, symmetry-aware PINN, quantum PDE solver, equivariant quantum circuit, GQPINN, quantum phys...

Geometric origin of exact mean-field reductions using Möbius symmetry and the Lorentzian Ansatz — proving the Cauchy-Lorentz family uniquely emerges as invariant under projective transport, unifying Ott-Antonsen and Montbrió-Pazó-Roxin reductions.

Geometric Basis Functions (GBF) framework for noninvasive whole human brain dynamics mapping using participant-specific eigenmodes derived from cortical geometry. Use when working with EEG/MEG source imaging, brain dynamics reconstruction, neuroimaging inverse problems, or cortical geometry-based neural activity mapping. Enables high-fidelity spatiotemporal reconstruction of neural sources using geometric constraints.

Geometric Basis Functions (GBF) methodology for noninvasive whole human brain dynamics mapping using participant-specific cortical eigenmodes. Reconstructs whole-brain spatiotemporal dynamics from EEG/MEG with anatomically-constrained source imaging. Activation - geometric basis functions, GBF, brain dynamics, source imaging, cortical geometry, EEG/MEG reconstruction.

Genetic and environmental architecture of human functional connectome using extended twin modeling. Separates measurement error from non-shared environment to estimate true connectivity heritability. Keywords: functional connectome, twin modeling, heritability, genetic architecture, brain connectivity.

Zero-shot imagined speech decoding from MEG via imagined-to-listened cross-condition mapping. Trains models to map imagined MEG responses to listened responses, then decodes using listened-only decoder. Three-stage pipeline: (1) mapping imagined→listened MEG, (2) train contrastive word decoder on listened MEG with multi-embedding evaluation, (3) decode imagined speech via mapping pipeline on held-out subjects. Use when: imagined speech decoding, MEG BCI, cross-condition neural mapping, zero-s...

**arXiv ID:** 2003.08561 **Authors:** Sung Whan Yoon, Do-Yeon Kim, Jun Seo, Jaekyun Moon **Published:** 2020-03-19T04:02:44Z **Abstract:** Learning novel concepts while preserving prior knowledge is a long-standing challenge in machine learning. The challenge gets greater when a novel task is given with only a few labeled examples, a problem known as incremental few-shot learning. We propose XtarNet, which learns to extract task-adaptive representation (TAR) for facilitating incremental few-s...

Wavelet-Enhanced Mixture-of-Experts (WaveMoE) foundation model for time series forecasting. Use when building time series prediction models, incorporating frequency-domain information, or designing MoE architectures for temporal data.