Paper proposes efficient approach for fault identification in structures.
problem Challenging fault identification using impedance/admittance measurements.
method Many-objective optimization with Gaussian process calibration and voting score calculation.
result Efficient fault identification without iterative finite element analysis.
Seismic inversion improved using semi-supervised sequence modeling.
problem Lack of geophysical constraints in machine learning seismic inversion.
method Semi-supervised sequence modeling with recurrent neural networks.
result Achieved 98% correlation between estimated and target elastic impedance.
Deep network improves electrical tomography across multiple frequencies.
problem Nonlinear multi-frequency electrical impedance tomography (mfEIT) for tissue conductivity estimation.
method Integrates graph neural networks (GNNs) into the iterative Proximal Regularized Gauss Newton (PRGN) framework to reconstruct tissue concentrations accurately.
result Accurate reconstruction of overlapping tissue fraction concentrations across multiple frequencies.
Neural net solves PDEs without labels, useful for EIT.
problem Solving PDEs for electrical impedance tomography.
method Unsupervised deep learning with neural network minimizer.
result Deep neural network approximates PDE solutions.
This paper describes a pattern recognition approach aiming to estimate fuel cell duration time from electrochemical impedance spectroscopy measurements. It consists in first extracting features from both real and imaginary parts of the impedance spectrum. A parametric model is considered in the case of the real part, w…
Adam's hyperparameters implicitly regularize solutions, penalizing or impeding loss gradients' norms.
problem Implicit regularization in Adam's hyperparameters and training stage.
method Backward error analysis and ODE approximations to study Adam's behavior.
result Adam's implicit regularization depends on hyperparameters and training stage, involving different norms.
This study recovers electromagnetic parameters on boundaries from impedance and admittance data.
problem Recovering anisotropic electromagnetic parameters from boundary impedance and admittance data.
method Formulated inverse boundary value problem for time-harmonic Maxwell's equations on differential 1-forms.
result Knowledge of impedance and admittance maps determines tangential entries of induced metrics at the boundary.
This paper is an attempt to separate cardiac and respiratory signals from an electrical bio-impedance (EBI) dataset. For this two well-known algorithms, namely Principal Component Analysis (PCA) and Independent Component Analysis (ICA), were used to accomplish the task. The ability of the PCA and the ICA methods first …
Deep learning model improves seismic rock property estimation.
problem Estimating reservoir rock properties from seismic reflection data.
method Proposes a deep learning-based seismic inversion workflow that models seismic traces spatiotemporally.
result Achieves best performance on SEAM dataset with r2 coefficient of 79.77\% Study uses outer metrics for PDE-constrained shape optimization over diffeomorphism group.
problem Optimizing shapes governed by PDEs over the diffeomorphism group.
method Outer metrics on diffeomorphism group, Riemannian steepest descent method.
result Riemannian approach outperforms other metrics in solving PDE-constrained shape optimization problems.
Paper quantifies uncertainties in EIS spectra of SOFCs, proposing VB method for online monitoring.
problem Distortions in EIS spectra due to disturbances, drifts, and sensor noise.
method Proposes variational Bayes (VB) method for quantifying spectral uncertainty in EIS of SOFCs.
result VB method provides approximate distributions of ECM parameters with low computational load.
Introduces Relational Privacy (RP) to control relation memorization in question answering models.
problem Relation memorization in question answering models can lead to privacy issues.
method Formalizes Relational Privacy (RP) and Differential Relational Privacy (DrP), providing bounds on relation memorization.
result DrP allows effective learning of general properties of underlying concepts while preventing relation memorization.
The paper derives uncertainty quantification for ML models used in metrology.
problem Uncertainty quantification for ML models in metrology applications.
method Analytical expressions for mean and variance of model output are derived for various ML models.
result The derived expressions cover multiple ML models and are validated against Monte Carlo methods.
Study finds cryptoasset markets inefficient due to capital reallocation frictions.
problem Inefficiency in cryptoasset markets due to capital reallocation frictions.
method Examined investments with dominant and secondary risk factors, derived equilibrium restrictions, and tested empirically.
result Empirical results strongly reject necessary equilibrium restrictions, indicating market inefficiency.
Einstein metrics are blocked by manifold features and group growth.
problem Existence of Einstein metrics on specific 4-manifolds.
method Analysis of collapsing and group growth effects.
result Several 4-manifolds cannot support Einstein metrics due to specific features.
Optimizes PCB stack-up design for high-speed circuits.
problem Efficiently optimize many parameters in PCB stack-up design.
method Parallel and intelligent Bayesian optimization for stripline design.
result Improves accuracy and efficiency of PCB stack-up optimization.
Kernelized Support Vector Machines (SVMs) are among the best performing supervised learning methods. But for optimal predictive performance, time-consuming parameter tuning is crucial, which impedes application. To tackle this problem, the classic model selection procedure based on grid-search and cross-validation was …
Differentiable ABMs face challenges in inference and optimisation.
problem Challenges in parameter inference and optimisation for differentiable ABMs.
method Discussion and experiments highlighting challenges.
result Challenges remain in constructing differentiable ABMs.
Recurring international financial crises have adverse socioeconomic effects and demand novel regulatory instruments or strategies for risk management and market stabilization. However, the complex web of market interactions often impedes rational decisions that would absolutely minimize the risk. Here we show that, for…
New tool helps analyze complex financial data.
problem Difficulty in comprehending high-dimensional financial data.
method Topological Data Analysis Ball Mapper algorithm.
result Shows new way to see detail in financial data.
Most research on the interpretability of machine learning systems focuses on the development of a more rigorous notion of interpretability. I suggest that a better understanding of the deficiencies of the intuitive notion of interpretability is needed as well. I show that visualization enables but also impedes intuitiv…
The study examines conditions that prevent null geodesic lines in spacetimes, impacting cosmological geometry.
problem Preventing the existence of null geodesic lines in spacetimes.
method Identifying geometric conditions on foliations of spacetimes that prevent null geodesic lines, especially for spacetimes with compact Cauchy hypersurfaces.
result Conditions on foliations can prevent null geodesic lines, leading to restrictions on cosmological spacetime geometry.
Efficiently scales continuous kernels with sparse Fourier domain learning.
problem High computational and memory demands, spectral bias in continuous kernels.
method Sparse learning in the Fourier domain.
result Efficient scaling of continuous kernels, reduced computational and memory requirements, mitigated spectral bias.
Study uses deep learning to predict asset prices, finds complex target processes lead to meaningless predictions.
problem Complexity of successful price prediction models hinders understanding.
method Deep learning models for high-frequency price prediction, focusing on volatility and directional prediction.
result Inadequately defined target price process renders predictions meaningless.
The ability to learn from a small number of examples has been a difficult problem in machine learning since its inception. While methods have succeeded with large amounts of training data, research has been underway in how to accomplish similar performance with fewer examples, known as one-shot or more generally few-sh…
New insights into neural network training efficiency.
problem Understanding the optimal initialization for deep neural networks.
method Exploring the edge of chaos and saturation of tanh activation function.
result The line of uniformity in phase space intersects the edge of chaos, indicating saturation begins to hinder training efficiency.
The Dirichlet-to-Neumann map for differential forms on a Riemannian manifold with boundary is a generalization of the classical Dirichlet-to-Neumann map which arises in the problem of Electrical Impedance Tomography. We synthesize the two different approaches to defining this operator by giving an invariant definition …
We propose an inference method to estimate sparse interactions and biases according to Boltzmann machine learning. The basis of this method is L1 regularization, which is often used in compressed sensing, a technique for reconstructing sparse input signals from undersampled outputs. L1 regularization impedes the …
The Gibbs sampler is a particularly popular Markov chain used for learning and inference problems in Graphical Models (GMs). These tasks are computationally intractable in general, and the Gibbs sampler often suffers from slow mixing. In this paper, we study the Swendsen-Wang dynamics which is a more sophisticated Mark…
Optimal transport (OT) distances are finding evermore applications in machine learning and computer vision, but their wide spread use in larger-scale problems is impeded by their high computational cost. In this work we develop a family of fast and practical stochastic algorithms for solving the optimal transport probl…
Water saturation is an important property in reservoir engineering domain. Thus, satisfactory classification of water saturation from seismic attributes is beneficial for reservoir characterization. However, diverse and non-linear nature of subsurface attributes makes the classification task difficult. In this context,…
Regularized training of an autoencoder typically results in hidden unit biases that take on large negative values. We show that negative biases are a natural result of using a hidden layer whose responsibility is to both represent the input data and act as a selection mechanism that ensures sparsity of the representati…
Novel approach analyzes ReLU networks' training dynamics and proposes GmP for improved optimization.
problem Stochastic optimization instability in ReLU networks impedes convergence and generalization.
method Characteristic activation boundaries analysis and Geometric Parameterization (GmP) technique.
result GmP resolves instability, leading to better optimization, convergence, and generalization.
Paper develops formulas for shape derivatives in wave scattering.
problem Computing high order shape derivatives for wave scattering is challenging.
method Introduces elegant recurrence formulas using differential forms and Lie derivatives.
result Unified framework for computing high order shape perturbations in scattering problems.
Deep Relevance Regularization improves neural network performance in tumor typing.
problem Confounding factors hinder neural network performance in multi-laboratory imaging mass spectrometry data.
method Introduces Deep Relevance Regularization to restrict neural network focus.
result Deep Relevance Regularization robustifies neural networks and improves interpretability.
A network removes irrelevant structures from chest radiographs for better analysis.
problem Clutter in chest radiographs hinders visual inspection and analysis.
method Fully Convolutional Network to suppress undesired visual structure.
result Improved classifier performance with limited training data.
AB dynamically scales gradients to mitigate asynchronous training delays.
problem Gradient delay in asynchronous training reduces model performance.
method Adaptive Braking (AB) dynamically scales gradients based on alignment.
result AB enables training with up to 32 update steps of delay without accuracy loss.
Enhanced anomaly detection using PRC-RF with autoencoders.
problem Extreme class imbalance and curse of dimensionality in anomaly detection.
method Hybrid framework combining PRC-RF and autoencoders.
result Autoencoder-PRC-RF model outperforms previous methods in accuracy, scalability, and interpretability.
Pruning improves DNNs against MIA while reducing model size and computation.
problem Vulnerability of DNNs to membership inference attacks (MIA).
method Proposes a pruning algorithm to reduce model size and computational operations.
result Pruned subnetwork prevents privacy leakage from MIA with competitive accuracy.
Genome-wide association studies have proven to be essential for understanding the genetic basis of disease. However, many complex traits---personality traits, facial features, disease subtyping---are inherently high-dimensional, impeding simple approaches to association mapping. We developed a nonparametric Bayesian re…
Analyzes adversarial training's impact on loss landscape, proposing PAS to improve model performance.
problem Challenges in optimizing models under adversarial training due to loss landscape properties.
method Analytical studies of adversarial loss functions, numerical analyses, PAS strategy.
result Adversarial training impairs optimization, but PAS strategy improves model performance.
BCV method helps estimate clusters and hyper-parameters in large data sets.
problem Determining the number of clusters in large-scale data.
method Bi-cross validation (BCV) for spectral clustering.
result BCV directly applies to spectral clustering for estimating clusters and hyper-parameters.
Score function estimators improve k-subset sampling efficiency.
problem Efficiently sampling k-subsets in machine learning tasks. method Revisit score function estimators, using discrete Fourier transform and control variates.
result Efficient and unbiased gradient estimates for k-subset sampling. New measures detect HFT activity, revealing its impact on stock prices.
problem Lack of public data on HFT activity.
method Developed machine learning models to predict HFT activity using proprietary and public data.
result Measures outperform conventional proxies and reveal HFT's impact on price discovery.
Proposes a method to prevent neural networks from forgetting learned tasks.
problem Catastrophic forgetting in neural networks.
method Attention-based selective plasticity of synapses inspired by the cholinergic neuromodulatory system.
result Competitive performance on benchmark tasks compared to state-of-the-art methods.
Paper introduces a new gradient estimator for SNNs.
problem High variance in score function gradient estimator impedes SNNs training.
method Developed a differentiable point process to derive path-wise gradient estimator.
result Demonstrated effectiveness of path-wise gradient estimator through simulations.
Due to the rapid growth of data and computational resources, distributed optimization has become an active research area in recent years. While first-order methods seem to dominate the field, second-order methods are nevertheless attractive as they potentially require fewer communication rounds to converge. However, th…
Neural network HDP improves virtual inertia control for non-inductive grids.
problem Traditional virtual inertia controllers are not suitable for non-inductive grids.
method Adaptive neural network heuristic dynamic programming (HDP) for optimal control.
result The proposed HDP controller outperforms traditional controllers in virtual inertia control.