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.
When using Convolutional Neural Networks (CNNs) for segmentation of organs and lesions in medical images, the conventional approach is to work with inputs and outputs either as single slice (2D) or whole volumes (3D). One common alternative, in this study denoted as pseudo-3D, is to use a stack of adjacent slices as in…
Transformer-M learns molecular data in 2D or 3D formats.
Enhances 2D face recognition with 3D features using active illumination.
Extends L2-norm LDA to 2D inputs using Bhattacharyya bound.
Test for linearizing 2-input systems with 2D feedback.
The paper studies how grid cell patterns emerge in neural networks.
Self attention mechanisms have become a key building block in many state-of-the-art language understanding models. In this paper, we show that the self attention operator can be formulated in terms of 1x1 convolution operations. Following this observation, we propose several novel operators: First, we introduce a 2D ve…
This paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats. We design a 1D-CNN that directly learns features from raw heart-sound signals, and a 2D-CNN that takes inputs of two- dimensional time-frequency fea…
The paper uses facial keypoints to estimate post-surgical pain intensity.
Deep learning network matches radiologists in breast cancer segmentation.
STRING improves 2D and 3D position encodings for better performance.
3D object classification and segmentation using deep neural networks has been extremely successful. As the problem of identifying 3D objects has many safety-critical applications, the neural networks have to be robust against adversarial changes to the input data set. There is a growing body of research on generating h…
This work demonstrates a physical attack on a deep learning image classification system using projected light onto a physical scene. Prior work is dominated by techniques for creating adversarial examples which directly manipulate the digital input of the classifier. Such an attack is limited to scenarios where the adv…
IANN visualizes all input variables effects simultaneously.
RNNs and their variants have been widely adopted for image captioning. In RNNs, the production of a caption is driven by a sequence of latent states. Existing captioning models usually represent latent states as vectors, taking this practice for granted. We rethink this choice and study an alternative formulation, name…
In this paper, we present a deep-learning based method for estimating the 3D structure of a bone from a pair of 2D X-ray images. Our triplet loss-trained neural network selects the most closely matching 3D bone shape from a predefined set of shapes. Our predictions have an average root mean square (RMS) distance of 1.0…
An active learner chooses which data points to label to minimize cost and error in streaming data.
2D CNNs approximate Korobov functions with near-optimal rates.
Proposes a model to generate 3D-aware images from 2D images.
The data of a "2D field theory with a closed string compactification" is an equivariant chain level action of a cell decomposition of the union of all moduli spaces of punctured Riemann surfaces with each component compactified as a pseudomanifold with boundary. The axioms on the data are contained in the following ass…
Derive bihamiltonian structure for rational reduction of 2D-Toda hierarchy
We present a novel approach to automatically segment magnetic resonance (MR) images of the human brain into anatomical regions. Our methodology is based on a deep artificial neural network that assigns each voxel in an MR image of the brain to its corresponding anatomical region. The inputs of the network capture infor…
This study improves lung tumor segmentation in mice MRI scans with nnU-Net, reducing annotation needs.
For many automated driving functions, a highly accurate perception of the vehicle environment is a crucial prerequisite. Modern high-resolution radar sensors generate multiple radar targets per object, which makes these sensors particularly suitable for the 2D object detection task. This work presents an approach to de…
New method reconstructs 3D shapes from 2D images using Kendall's shape space.
The paper establishes T-duality for 2D σ-models with H-flux.
New theorem shows embedding restrictions for manifold skeletons.
Contrastive learning recovers latent distributions for ambiguous inputs, including aleatoric uncertainty.
Computes a new metric quantity Y(M) for Riemannian 2d-manifolds.
The demand for fast and accurate structural analysis is becoming increasingly more prevalent with the advance of generative design and topology optimization technologies. As one step toward accelerating structural analysis, this work explores a deep learning based approach for predicting the stress fields in 2D linear …
Study 2D viscoelastic equations using Lie group theory.
DISPR uses diffusion models to predict 3D cell shapes from 2D images.
iSTFTNet2 improves iSTFTNet's speed and lightness with 1D-2D CNN.
This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It requires no other tool than the backpropagation algorithm to learn its parameters whi…
Paper extends 2D ZSAD to 3D MRI without training, achieving robust anomaly detection.
Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.
In this paper, we have proposed a brain signal classification method, which uses eigenvalues of the covariance matrix as features to classify images (topomaps) created from the brain signals. The signals are recorded during the answering of 2D and 3D questions. The system is used to classify the correct and incorrect a…
3D shape instantiation which reconstructs the 3D shape of a target from limited 2D images or projections is an emerging technique for surgical intervention. It improves the currently less-informative and insufficient 2D navigation schemes for robot-assisted Minimally Invasive Surgery (MIS) to 3D navigation. Previously,…
The introduction of convolutional layers greatly advanced the performance of neural networks on image tasks due to innately capturing a way of encoding and learning translation-invariant operations, matching one of the underlying symmetries of the image domain. In comparison, there are a number of problems in which the…
Universal Gaussian parity proven for 2D knots.
In this paper, we propose to provide a general ensemble learning framework based on deep learning models. Given a group of unit models, the proposed deep ensemble learning framework will effectively combine their learning results via a multilayered ensemble model. In the case when the unit model mathematical mappings a…
We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary work on applying Reinforcement Learning to such setting, on 2D navigation tasks…
There is a growing need for fast and accurate methods for testing developmental neurotoxicity across several chemical exposure sources. Current approaches, such as in vivo animal studies, and assays of animal and human primary cell cultures, suffer from challenges related to time, cost, and applicability to human physi…
Study classifies equidistant decompositions in 2D spaces.
We describe rules for building 2d theories labeled by 4-manifolds. Using the proposed dictionary between building blocks of 4-manifolds and 2d N=(0,2) theories, we obtain a number of results, which include new 3d N=2 theories T[M_3] associated with rational homology spheres and new results for Vafa-Witten partition fun…
The paper introduces various canonical parameterizations for 2D-curved shapes.
This research uses Siamese networks to identify partial mouse brain images from the Allen atlas.
Characterization of lung nodules as benign or malignant is one of the most important tasks in lung cancer diagnosis, staging and treatment planning. While the variation in the appearance of the nodules remains large, there is a need for a fast and robust computer aided system. In this work, we propose an end-to-end tra…