arXiv research

Machine learning predicts NaV1.7 inhibitors, leading to effective drug K1.

Framework detects and classifies multi-label RBC images from microscopic images.

We develop a stochastic whole-brain and body simulator of the nematode roundworm Caenorhabditis elegans (C. elegans) and show that it is sufficiently regularizing to allow imputation of latent membrane potentials from partial calcium fluorescence imaging observations. This is the first attempt we know of to "complete t…

A method uses autoencoders to align multi-modal neuron data.

The paper sets lower bounds for Laplacian eigenvalues and clamped plate problem eigenvalues.

Affirm Lord Rayleigh's conjecture on curved spaces for clamped plates.

In this paper, we study eigenvalues of a clamped plate problem. We obtain a lower bound for eigenvalues, which gives an important improvement of results due to Levine and Protter.

We examine the effect of clamping variables for approximate inference in undirected graphical models with pairwise relationships and discrete variables. For any number of variable labels, we demonstrate that clamping and summing approximate sub-partition functions can lead only to a decrease in the partition function e…

In this paper, we study estimates for eigenvalues of the clamped plate problem. A sharp upper bound for eigenvalues is given and the lower bound for eigenvalues in [10] is improved.

Malaria is a female anopheles mosquito-bite inflicted life-threatening disease which is considered endemic in many parts of the world. This article focuses on improving malaria detection from patches segmented from microscopic images of red blood cell smears by introducing a deep convolutional neural network. Compared …

For a bounded domain $Ω$ in a complete Riemannian manifold $M^n$, we study estimates for lower order eigenvalues of a clamped plate problem. We obtain universal inequalities for lower order eigenvalues. We would like to remark that our results are sharp.

New isoperimetric inequality for clamped plates in RCD(0,N) spaces, sharp and stable.

Study curves evolving by gradient flow of elastic energy, proving existence, smoothing, and convergence.

This paper studies eigenvalues of the clamped plate problem on a bounded domain in an $n$-dimensional Euclidean space. We give an estimate for the gap between $\sqrt {Γ_{k+1}-Γ_{1}}$ and $\sqrt {Γ_{k}-Γ_{1}}$, for any positive integer $k$. According to the asymptotic formula of Agmon and Pleijel, we know, the gap betwe…

CLAMP uses neural manifold packing to improve self-supervised learning.

The paper studies eigenvalue inequalities for a clamped plate problem involving a generalized elliptic differential operator.

Proves Payne conjecture for buckling and membrane eigenvalues.

We study Lord Rayleigh's problem for clamped plates on an arbitrary $n$-dimensional $(n\geq 2)$ Cartan-Hadamard manifold $(M,g)$ with sectional curvature $\textbf{K}\leq -κ^2$ for some $κ\geq 0.$ We first prove a McKean-type spectral gap estimate, i.e. the fundamental tone of any domain in $(M,g)$ is universally bounde…

Euler's elastica with monotone curvature is uniquely minimal.

Paper studies eigenvalues of a specific operator on Riemannian manifolds.

Extends plate problems to differential forms on manifolds.

Defense against small image patches using occlusions.

Proposes a new approach to time series representation learning by embedding patches independently.

Paper proves rigidity estimates for hyperbolic shells and applies them to \(Γ\)-limit theory.

In this report we investigate fundamental requirements for the application of classifier patching on neural networks. Neural network patching is an approach for adapting neural network models to handle concept drift in nonstationary environments. Instead of creating or updating the existing network to accommodate conce…

New method makes neural networks more resilient to location-optimized adversarial patches.

Paper presents certified defenses against adversarial patch attacks.

Neural networks are commonly trained to make predictions through learning algorithms. Contrastive Hebbian learning, which is a powerful rule inspired by gradient backpropagation, is based on Hebb's rule and the contrastive divergence algorithm. It operates in two phases, the forward (or free) phase, where the data are …

Reinforcement Patching optimizes dynamic sequence patching for efficient time series forecasting.

Analytic patch trees reveal new geometric structures and dimension fields.

MAT combines meta-learning and adversarial training to defend against universal patches.

Patch priors have become an important component of image restoration. A powerful approach in this category of restoration algorithms is the popular Expected Patch Log-Likelihood (EPLL) algorithm. EPLL uses a Gaussian mixture model (GMM) prior learned on clean image patches as a way to regularize degraded patches. In th…

New method defends against patch attacks with high-certainty guarantees.

BagCert efficiently certifies robustness against adversarial patches on image classifiers.

In this paper we address the problem of understanding the success of algorithms that organize patches according to graph-based metrics. Algorithms that analyze patches extracted from images or time series have led to state-of-the art techniques for classification, denoising, and the study of nonlinear dynamics. The mai…

The main ob jective of this research is to find the different types of elliptic triangulations for planar discs and spheres. We begin in Chapter 1 with the mandatory introduction. In the second chapter we define and study the notion of a patch, that is, a triangulation of a planar disc. By introducing a suitable notion…

Ano-SuPs detects anomalies in images of manufactured products by identifying suspected patches.

Patients initially diagnosed with early mild cognitive impairment (eMCI) are known to be a clinically heterogeneous group with very subtle patterns of brain atrophy. To examine the boarders between normal controls (NC) and eMCI, Magnetic Resonance Imaging (MRI) was extensively used as a non-invasive imaging modality to…

Universal adversarial patches prevent face detection in various frameworks.

Smooth compactness theorem for elasticae, except straight segments.

In this paper, we demonstrate a physical adversarial patch attack against object detectors, notably the YOLOv3 detector. Unlike previous work on physical object detection attacks, which required the patch to overlap with the objects being misclassified or avoiding detection, we show that a properly designed patch can s…

Sharp spectral gap estimates for higher-order operators on hyperbolic spaces.

There have been different strategies to improve the performance of a machine learning model, e.g., increasing the depth, width, and/or nonlinearity of the model, and using ensemble learning to aggregate multiple base/weak learners in parallel or in series. This paper proposes a novel strategy called patch learning (PL)…

Efficiently processes high res images by selecting relevant patches.

PatchGuard defends against localized adversarial patches with provable robustness.

Patch augmentation boosts neural network accuracy and robustness.

The original contributions of this paper are twofold: a new understanding of the influence of noise on the eigenvectors of the graph Laplacian of a set of image patches, and an algorithm to estimate a denoised set of patches from a noisy image. The algorithm relies on the following two observations: (1) the low-index e…

Recent work (Pennington et al, 2017) suggests that controlling the entire distribution of Jacobian singular values is an important design consideration in deep learning. Motivated by this, we study the distribution of singular values of the Jacobian of the generator in Generative Adversarial Networks (GANs). We find th…