Related papers: NNVub: a Neural Network Approach to $B\to X_u \ell…
The determination of $|V_{ub}|$ in inclusive semileptonic $B \to X_u \ell \nu$ decays will be among the pivotal tasks of Belle II. In this paper we study the potential and limitations of machine learning approaches that attempt to reduce…
Graph Neural Networks (GNNs) can predict the performance of an industrial design quickly and accurately and be used to optimize its shape effectively. However, to fully explore the shape space, one must often consider shapes deviating…
Deep learning greatly improved the realism of animatable human models by learning geometry and appearance from collections of 3D scans, template meshes, and multi-view imagery. High-resolution models enable photo-realistic avatars but at…
We report on the measurement of inclusive charmless semileptonic B decays $B \to X_{u} \ell \nu$. The analysis makes use of hadronic tagging and is performed on the full data set of the Belle experiment comprising 772 million $B\bar{B}$…
We construct a parametrization of the lepton energy spectrum in inclusive semileptonic decays of B mesons, based on the available experimental information: moments of the spectrum with cuts, their errors and their correlations, together…
The choice of the shape parameter highly effects the behaviour of radial basis function (RBF) approximations, as it needs to be selected to balance between ill-condition of the interpolation matrix and high accuracy. In this paper, we…
The total B->Xs gamma decay rate and the CKM-matrix element Vub play an important role in finding indirect evidence for new physics affecting the flavor sector of the Standard Model, complementary to direct searches at the LHC and Tevatron.…
We present ``state-of-the-art'' theoretical expressions for the triple differential B->X_u l^- nu decay rate and for the B->X_s gamma photon spectrum, which incorporate all known contributions and smoothly interpolate between the…
We describe and analyze algorithms for shape-constrained symbolic regression, which allows the inclusion of prior knowledge about the shape of the regression function. This is relevant in many areas of engineering -- in particular whenever…
The determination of |Vub| from inclusive semileptonic B decays is limited by uncertainties in modelling the decay distributions in b->ulnu transitions. The largest uncertainties arise from the limited knowledge of the appropriate b quark…
Artificial neural networks are functions depending on a finite number of parameters typically encoded as weights and biases. The identification of the parameters of the network from finite samples of input-output pairs is often referred to…
Representing shapes as level sets of neural networks has been recently proved to be useful for different shape analysis and reconstruction tasks. So far, such representations were computed using either: (i) pre-computed implicit shape…
We focus on semiparametric regression that has played a central role in statistics, and exploit the powerful learning ability of deep neural networks (DNNs) while enabling statistical inference on parameters of interest that offers…
Deep Neural nets (NNs) with millions of parameters are at the heart of many state-of-the-art computer vision systems today. However, recent works have shown that much smaller models can achieve similar levels of performance. In this work,…
State-of-the-art parametric and non-parametric style transfer approaches are prone to either distorted local style patterns due to global statistics alignment, or unpleasing artifacts resulting from patch mismatching. In this paper, we…
We propose a neural parameterization of convex sets by learning sublinear (positively homogeneous and convex) functions. Our networks implicitly represent both the support and gauge functions of a convex body. We prove a universal…
Formal verification of neural networks is essential for their deployment in safety-critical areas. Many available formal verification methods have been shown to be instances of a unified Branch and Bound (BaB) formulation. We propose a…
While current state-of-the-art generalizable implicit neural shape models rely on the inductive bias of convolutions, it is still not entirely clear how properties emerging from such biases are compatible with the task of 3D reconstruction…
Neural network (NN) denoisers are an essential building block in many common tasks, ranging from image reconstruction to image generation. However, the success of these models is not well understood from a theoretical perspective. In this…
Graph neural networks have emerged as a promising approach for the analysis of non-Euclidean data such as meshes. In medical imaging, mesh-like data plays an important role for modelling anatomical structures, and shape classification can…