A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper tackles shape graph registration using neural networks.
Paper analyzes shapes of brain arterial networks using statistical methods.
Shape adaptor learns flexible resizing factors for neural networks.
We introduce a wide and deep neural network for prediction of progression from patients with mild cognitive impairment to Alzheimer's disease. Information from anatomical shape and tabular clinical data (demographics, biomarkers) are fused in a single neural network. The network is invariant to shape transformations an…
A recent Cell paper [Chang and Tsao, 2017] reports an interesting discovery. For the face stimuli generated by a pre-trained active appearance model (AAM), the responses of neurons in the areas of the primate brain that are responsible for face recognition exhibit strong linear relationship with the shape variables and…
New findings connect shaped and unshaped neural networks using differential equations.
A neural network learns efficient parametrizations of product shape spaces.
Neural networks predict shapes of first passage percolation sets.
Large prospective epidemiological studies acquire cardiovascular magnetic resonance (CMR) images for pre-symptomatic populations and follow these over time. To support this approach, fully automatic large-scale 3D analysis is essential. In this work, we propose a novel deep neural network using both CMR images and pati…
Study on neural network initialization with shaped infinite depth-and-width networks.
PointGMM learns hGMMs from point clouds for 3D shape representation.
The paper presents a method for analyzing shape graphs using specific features.
This work characterizes how data augmentation shapes neural representations.
The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Inspired by the nature of human perception of 3D shapes as a collection of simple parts, we explore such an abstract shape represe…
FineHand learns hand shapes for better ASL recognition.
Convolutional Neural Networks (CNNs) have become the state-of-the-art method to learn from image data. However, recent research shows that they may include a texture and colour bias in their representation, contrary to the intuition that they learn the shapes of the image content and to human biological learning. Thus,…
SVarM uses varifold representations for shape classification and regression.
Cell nuclei detection is a challenging research topic because of limitations in cellular image quality and diversity of nuclear morphology, i.e. varying nuclei shapes, sizes, and overlaps between multiple cell nuclei. This has been a topic of enduring interest with promising recent success shown by deep learning method…
The importance of training robust neural network grows as 3D data is increasingly utilized in deep learning for vision tasks in robotics, drone control, and autonomous driving. One commonly used 3D data type is 3D point clouds, which describe shape information. We examine the problem of creating robust models from the …
We consider convex symmetric lens-shaped networks in R^2 that evolve under curve shortening flow. We show that the enclosed convex domain shrinks to a point in finite time. Furthermore, after appropriate rescaling the evolving networks converge to a self-similarly shrinking network, which we prove to be unique in an ap…
Analog BNNs perform similarly regardless of noise distribution shape.
Study S-shaped utility maximization with VaR constraint and unobservable drift.
Left atrium shape has been shown to be an independent predictor of recurrence after atrial fibrillation (AF) ablation. Shape-based representation is imperative to such an estimation process, where correspondence-based representation offers the most flexibility and ease-of-computation for population-level shape statisti…
New method learns shape correspondences robustly from raw geometry.
Over-parameterized CNNs show U-shaped test risk with depth increase.
Detection of cell nuclei in microscopic images is a challenging research topic, because of limitations in cellular image quality and diversity of nuclear morphology, i.e. varying nuclei shapes, sizes, and overlaps between multiple cell nuclei. This has been a topic of enduring interest with promising recent success sho…
Recent progress in deep generative models has led to tremendous breakthroughs in image generation. However, while existing models can synthesize photorealistic images, they lack an understanding of our underlying 3D world. We present a new generative model, Visual Object Networks (VON), synthesizing natural images of o…
New method uses cluster shapes to improve track finding in particle collisions.
We solve S-shaped utility portfolio selection with SD constraints using algorithms and neural networks.
In this paper, an unsupervised machine learning method for geometric constellation shaping is investigated. By embedding a differentiable fiber channel model within two neural networks, the learning algorithm is optimizing for a geometric constellation shape. The learned constellations yield improved performance to sta…
The paper explores a new method for landmark matching using sub-Riemannian geometry and neural networks.
We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers…
New neural network models extreme value distributions with preserved shape constraints.
Topology-enhanced loss improves 3D object reconstruction from 2D images.
New scheme optimizes BMI through probabilistic and geometric shaping.
Training shapes the geometry of neural network feature maps, revealing local area magnification.
ES-VAE models skeletal pose trajectories by removing nuisance factors.
The paper proposes a deep learning approach to efficiently approximate diffeomorphisms for shape alignment.
We present a method of generating high resolution 3D shapes from natural language descriptions. To achieve this goal, we propose two steps that generating low resolution shapes which roughly reflect texts and generating high resolution shapes which reflect the detail of texts. In a previous paper, the authors have show…
New deep learning method preserves orientation in shape matching.
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 representations; or (ii) loss functions explicitly defined over the neural level sets…
Bézier-GAN optimizes airfoil design by reducing shape complexity.
T-Basis represents neural network tensors with fewer parameters.
Information Cascades Model captures dynamical properties of user activity in a social network. In this work, we develop a novel framework for activity shaping under the Continuous-Time Information Cascades Model which allows the administrator for local control actions by allocating targeted resources that can alter the…
The paper reveals surprising star-shaped connectivity in neural networks.
Our work sheds new light on the role of oil prices in shaping the world economy by investigating flows of goods and services through global value chains between 1960 and 2011, by means of Markov Chain and network analysis. We show that over that time period the international division of labor and trade patterns are tig…
We study the curvature flow of planar nonconvex lens-shaped domains, considered as special symmetric networks with two triple junctions. We show that the evolving domain becomes convex in finite time; then it shrinks homothetically to a point. Our theorem is the analog of the result of Grayson for curvature flow of clo…
Polygonal meshes provide an efficient representation for 3D shapes. They explicitly capture both shape surface and topology, and leverage non-uniformity to represent large flat regions as well as sharp, intricate features. This non-uniformity and irregularity, however, inhibits mesh analysis efforts using neural networ…