arXiv research

PAC-Bayes framework fails on simple 1D linear classification task.

Improved robustness of 1D CNNs for heart arrhythmia classification.

Study on the complexity of 1D ReLU neural networks, proving growth in linear regions.

Soil texture is important for many environmental processes. In this paper, we study the classification of soil texture based on hyperspectral data. We develop and implement three 1-dimensional (1D) convolutional neural networks (CNN): the LucasCNN, the LucasResNet which contains an identity block as residual network, a…

A simple block configures optimal kernel sizes for time series classification.

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…

CNN improves OSA diagnosis accuracy from PSG data.

Linear RNNs exhibit a bias towards shorter memory due to initialization variance.

The paper proposes an ensemble of convolution-based methods for fault detection in gearboxes.

PixelHop++ improves image classification with a smaller model size.

A new tensor network method for image classification reduces computation cost.

Study how pairs of 1D foliations can be deformed into contact structures.

iSTFTNet2 improves iSTFTNet's speed and lightness with 1D-2D CNN.

In this paper, we present an end-to-end approach for environmental sound classification based on a 1D Convolution Neural Network (CNN) that learns a representation directly from the audio signal. Several convolutional layers are used to capture the signal's fine time structure and learn diverse filters that are relevan…

Split learning preserves privacy in 1D CNN models for detecting heart abnormalities.

Ridgeless ReLU networks interpolate datasets and extrapolate based on curvature signs.

A new deep learning benchmark reduces resource needs.

SCORE technique reduces BO's high-dimensional search costs.

Deep neural networks continue to show improved performance with increasing depth, an encouraging trend that implies an explosion in the possible permutations of network architectures and hyperparameters for which there is little intuitive guidance. To address this increasing complexity, we propose Evolutionary DEep Net…

A new method for efficient optimal partial transport in 1D.

Gradient descent trains shallow neural networks to approximate functions in 1D.

New method reduces PDE model parameters by 30% with sparsity.

Study uses 1D-CNNs to forecast mortality in ELSA survey.

This paper reconstructs equivalence classes in 1D neural networks.

3D topological order linked to Seifert manifolds and gauge groups.

We call a learner super-teachable if a teacher can trim down an iid training set while making the learner learn even better. We provide sharp super-teaching guarantees on two learners: the maximum likelihood estimator for the mean of a Gaussian, and the large margin classifier in 1D. For general learners, we provide a …

Supervised dimensionality reduction has emerged as an important theme in the last decade. Despite the plethora of models and formulations, there is a lack of a simple model which aims to project the set of patterns into a space defined by the classes (or categories). To this end, we set up a model in which each class i…

Connectedness proved for $\mathbb{Z}^d$ actions on 1D manifolds by $C^2$ diffeomorphisms.

Study shows how 3+1D cosmologies can evolve to de Sitter space under certain conditions.

HybridSGD improves SGD performance by balancing computation and communication.

Uniqueness of 1D bi-Schrödinger flow proven from flat torus to compact space.

New method uses neural networks to interpolate stellar atmospheres with high precision.

Estimates reliability of nuclear fuel using advanced modeling techniques.

Master thesis applies deep learning to sEMG hand gesture recognition, improving accuracy.

Paper extends multi-task Gaussian Cox processes for heterogeneous tasks.

Question classification (QC) is the primary step of the Question Answering (QA) system. Question Classification (QC) system classifies the questions in particular classes so that Question Answering (QA) System can provide correct answers for the questions. Our system categorizes the factoid type questions asked in natu…

Study shows inflation in 3+1D cosmologies with bounded scalar potential and specific symmetry.

Morphological neurons, that is morphological operators such as dilation and erosion with learnable structuring elements, have intrigued researchers for quite some time because of the power these operators bring to the table despite their simplicity. These operators are known to be powerful nonlinear tools, but for a gi…

Calibration of stochastic local volatility (SLV) models to their underlying local volatility model is often performed by numerically solving a two-dimensional non-linear forward Kolmogorov equation. We propose a novel finite volume (FV) discretization in the numerical solution of general 1D and 2D forward Kolmogorov eq…

We present a novel method of compression of deep Convolutional Neural Networks (CNNs) by weight sharing through a new representation of convolutional filters. The proposed method reduces the number of parameters of each convolutional layer by learning a 1D vector termed Filter Summary (FS). The convolutional filters ar…

Estimates latent positions in 1D torus from noisy pairwise affinities.

Inspired by chaotic firing of neurons in the brain, we propose ChaosNet -- a novel chaos based artificial neural network architecture for classification tasks. ChaosNet is built using layers of neurons, each of which is a 1D chaotic map known as the Generalized Luroth Series (GLS) which has been shown in earlier works …

This study analyzes a non-orientable spacetime model in 1+1D quantum gravity.

Capsule networks excel in understanding spatial relationships in 2D data for vision related tasks. Even though they are not designed to capture 1D temporal relationships, with TimeCaps we demonstrate that given the ability, capsule networks excel in understanding temporal relationships. To this end, we generate capsule…

The identification of novel drug-target (DT) interactions is a substantial part of the drug discovery process. Most of the computational methods that have been proposed to predict DT interactions have focused on binary classification, where the goal is to determine whether a DT pair interacts or not. However, protein-l…

In this paper, we present an acoustic scene classification framework based on a large-margin factorized convolutional neural network (CNN). We adopt the factorized CNN to learn the patterns in the time-frequency domain by factorizing the 2D kernel into two separate 1D kernels. The factorized kernel leads to learn the m…

Topological Quantum Field Theories (TQFTs) pertinent to some emergent low energy phenomena of condensed matter lattice models in 2+1 and 3+1D are explored. Many of our field theories are highly-interacting without free quadratic analogs. Some of our bosonic TQFTs can be regarded as the continuum field theory formulatio…

IETNet identifies important channels for MVTS classification.