## 594

new preprints about computer science in the last week

## arXiv

most active server in computer science in the last week

### state of the art

34 preprints

Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings

We investigate multi-speaker modeling for end-to-end text-to-speech synthesis and study the effects of different types of state-of-the-art neural speaker embeddings on speaker similarity for unseen speakers.
3 days ago
arXiv

Self-Attention for Raw Optical Satellite Time Series Classification

Finally, we look into the self-attention transformer model and visualize attention scores as bipartite graphs in the context of the input time series and a low-dimensional representation of internal hidden states using t-distributed stochastic neighborhood embedding (t-SNE).
3 days ago
arXiv

Stain Style Transfer using Transitive Adversarial Networks

Compared with the state-of-the-art methods, our method yields an improvement of 0.87dB in terms of PSNR, demonstrating the effectiveness of the proposed TAN method in stain style transfer.
4 days ago
arXiv

### neural networks

27 preprints

Vanishing Nodes: Another Phenomenon That Makes Training Deep Neural Networks Difficult

The theoretical results show that the effective number of nodes vanishes to one when the VNI increases to one (its maximal value), and that vanishing/exploding gradients and vanishing nodes are two different challenges that increase the difficulty of training deep neural networks.
5 days ago
arXiv

ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks

To predict the mechanosensitive force response, we develop neural message passing networks and residual gated graph convnets which predict the protein dependent force separation at 86.63 percent, 81.59 kJ/mol/nm MAE, 76.99 psec MAE for force mode classification, max force magnitude, max force time respectively-- significantly...
5 days ago
arXiv

Overcoming the curse of dimensionality for some Hamilton--Jacobi partial differential equations via neural network architectures

These results do not rely on universal approximation properties of neural networks; rather, our results show that some classes of neural network architectures naturally encode the physics contained in some HJ PDEs.
6 days ago
arXiv

### deep learning

21 preprints

Applying deep learning to teleseismic phase detection and picking: PcP and PKiKP cases

In this study, we detect and pick the PcP and PKiKP phases from a Hinet dataset with 7386 seismograms by applying a deep-learning-based scheme.
6 days ago
arXiv

Test-time augmentation for deep learning-based cell segmentation on microscopy images

Deep learning network architectures have a large number of parameters, thus, in order to reach high accuracy, they require massive amount of annotated data.
4 days ago
bioRxiv

Multi-omics-based pan-cancer prognosis prediction using an ensemble of deep-learning and machine-learning models

Furthermore, models built on closely related cancer types using DeepProg are predictive of the subtypes of some other cancers, demonstrating the utility of DeepProg for transfer learning.
1 day ago
medRxiv

### machine learning

17 preprints

Distinguishing between paediatric brain tumour types using multi-parametric magnetic resonance imaging and machine learning: a multi-site study

The results show that diffusion and perfusion weighted imaging of both the tumour and whole brain provide significant features which differ between tumour types, and that combining these features gives the optimal machine learning classifier with greater than 80 percent predictive precision.
5 days ago
arXiv

Machine Learning for Inferring CO2 Fluxes: The New Metaphysics of Neural Nets

A non-intuitive machine learning metaphysical result was observed by the omission of CO2 concentrations as an input variable.
2 days ago
EarthArXiv

Multi-omics-based pan-cancer prognosis prediction using an ensemble of deep-learning and machine-learning models

We introduce DeepProg, a new computational framework that robustly predicts patient survival subtypes based on multiple types of omic data, using an ensemble of deep-learning and machine-learning models.
1 day ago
medRxiv

### reinforcement learning

10 preprints

Dealing with Sparse Rewards in Reinforcement Learning

This project introduces a novel reinforcement learning solution, by combining aspects of two existing state of the art sparse reward solutions.
5 days ago
arXiv

Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics

Our goal is to ensure the safety of a control policy trained using reinforcement learning, e.g., in a simulated environment.
3 days ago
arXiv

Reciprocal Collision Avoidance for General Nonlinear Agents using Reinforcement Learning

To reduce online computation, we first decompose the multi-agent scenario and solve a two agents collision avoidance problem using reinforcement learning (RL).
3 days ago
arXiv

### experiments show

8 preprints

Vanishing Nodes: Another Phenomenon That Makes Training Deep Neural Networks Difficult

Finally, the experiments show that the likelihood of failed training increases as the depth of the network increases.
5 days ago
arXiv

Inheritance without reactivation: Insights from crustal-scale analogue experiments

Our experiments show that a pervasive, vertically layered, mm-wide lower crustal anisotropy creates “extension-oblique” rift faults in the overlying basin within the upper crust.
3 days ago
EarthArXiv

Contextual Prediction Difference Analysis

The experiments show the superiority of our method by explaining image classifications of the state-of-the-art deep convolutional neural networks.
6 days ago
arXiv

### based approach

7 preprints

Self-Supervised Physics-Based Deep Learning MRI Reconstruction Without Fully-Sampled Data

This has implications for physics-based inverse problem approaches for other settings, where fully-sampled data is not available or possible to acquire.
6 days ago
arXiv

Ordering-Based Causal Structure Learning in the Presence of Latent Variables

While current algorithms for causal structure discovery in the presence of latent confounders are constraint-based, we here propose a score-based approach.
6 days ago
arXiv

### proposed approach

7 preprints

A Hybrid Semantic Parsing Approach for Tabular Data Analysis

Our proposed approach consists of: (1) a novel data abstraction step before the parser to make parsing table-agnosticism; (2) a set of semantic rules for parsing abstracted data-analysis questions to intermediate logic forms as tree derivations to reduce the search space; (3) a neural-based model as a local scoring...
3 days ago
arXiv

Bayesian nonparametric temporal dynamic clustering via autoregressive Dirichlet priors

Advantages of the proposed approach include flexibility in applications, ease of computations and interpretability.
3 days ago
arXiv

Long-Term Urban Vehicle Localization Using Pole Landmarks Extracted from 3-D Lidar Scans

Second, we show that the proposed approach clearly outperforms a recently published method in terms of accuracy.
3 days ago
arXiv

7 preprints

Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders

Purpose: To assess whether a generative adversarial network (GAN) could synthesize realistic optical coherence tomography (OCT) images that satisfactorily serve as the educational images for retinal specialists and the training datasets for the classification of various retinal disorders using deep learning (DL).
5 days ago
arXiv

Image Difficulty Curriculum for Generative Adversarial Networks (CuGAN)

Despite the significant advances in recent years, Generative Adversarial Networks (GANs) are still notoriously hard to train.
6 days ago
arXiv

Facial Expression Restoration Based on Improved Graph Convolutional Networks

Considering the correlations among different facial local regions under different facial expressions, this paper proposes a novel facial expression restoration method based on generative adversarial network by integrating an improved graph convolutional network (IGCN) and region relation modeling block (RRMB).
3 days ago
arXiv

### training data

7 preprints

Coercing Machine Learning to Output Physically Accurate Results

Many machine/deep learning artificial neural networks are trained to simply be interpolation functions that map input variables to output values interpolated from the training data in a linear/nonlinear fashion.
5 days ago
arXiv

Semantic Segmentation of Skin Lesions using a Small Data Set

Training data should be cropped to reduce complexity and augmented during training to reduce the likelihood of overfitting.
3 days ago
arXiv

Region Based Adversarial Synthesis of Facial Action Units

Extensive qualitative and quantitative evaluations are conducted on the commonly used BP4D dataset to verify the effectiveness of our proposed AU synthesis method.
4 days ago
arXiv

### state of the art performance

6 preprints

DeepSeqPanII: an interpretable recurrent neural network model with attention mechanism for peptide-HLA class II binding prediction

The leave-one-allele-out cross validation and benchmark evaluation results show that our proposed network model achieved state-of-the-art performance in HLA-II peptide binding.
2 days ago
bioRxiv

Inception Capsule Network for Retinal Blood Vessel Segmentation and Centerline Extraction

Our method achieved state-of-the-art performance for vessel segmentation and outperformed existing methods for centerline extraction.
5 days ago
bioRxiv

An Adaptive Empirical Bayesian Method for Sparse Deep Learning

Empirical applications of the proposed method lead to the state-of-the-art performance on MNIST and Fashion MNIST with shallow convolutional neural networks (CNN) and the state-of-the-art compression performance on CIFAR10 with Residual Networks.
3 days ago
arXiv

### numerical experiments

6 preprints

Finite Element Error Analysis of Surface Stokes Equations in Stream Function Formulation

We consider a surface Stokes problem in stream function formulation on a simply connected oriented surface $\Gamma \subset \mathbb{R}^3$ without boundary.
5 days ago
arXiv

Highly efficient and accurate schemes for time fractional Allen-Cahn equation by using extended SAV approach

The main contributions of the paper consist in: 1) constructing first and higher order unconditionally stable schemes for different mesh types, and proving the unconditional stability of the constructed schemes for the uniform mesh; 2) carrying out numerical experiments to verify the efficiency of the schemes and to...
6 days ago
arXiv

Explicit stabilized integrators for stiff optimal control problems

Numerical experiments including the optimal control of a nonlinear diffusion-advection PDE illustrate the efficiency of the new approach.
3 days ago
arXiv

### data analysis

5 preprints

A Hybrid Semantic Parsing Approach for Tabular Data Analysis

We also achieve promising results on a small dataset for more complex queries in both English and Chinese, which demonstrates our language expansion and quick-start ability.
3 days ago
arXiv

Identification of facet models by means of factor rotation: A simulation study and data analysis of a test for the Berlin Model of Intelligence Structure

Analysis of data of 393 participants that performed a test for the Berlin Model of Intelligence Structure revealed that the faceted structure of this model could be found by means of target rotation of task aggregates corresponding to the cross-products of the facets.
4 days ago
PsyArXiv

Design and Analysis of Cluster-Randomized Field Experiments in Panel Data Settings

While convenient, subsequent data analysis may be complicated by the constraint on the number of clusters in treatment and control.
6 days ago
NBER

### graph convolutional

5 preprints

Facial Expression Restoration Based on Improved Graph Convolutional Networks

Unlike conventional graph convolutional networks taking vectors as input features, IGCN can use tensors of face patches as inputs.
3 days ago
arXiv

Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection

This paper proposes an end-to-end deep learning framework for facial AU detection with graph convolutional network (GCN) for AU relation modeling, which has not been explored before.
4 days ago
arXiv

Semantic Graph Convolutional Network for Implicit Discourse Relation Classification

In this paper, we propose a novel and effective Semantic Graph Convolutional Network (SGCN) to enhance the modeling of inter-argument semantics on a deeper interaction level for implicit discourse relation classification.
5 days ago
arXiv

### attention based

5 preprints

Selective Attention Based Graph Convolutional Networks for Aspect-Level Sentiment Classification

Therefore we design a selective attention based GCN block (SA-GCN) to find the most important context words, and directly aggregate these information into the aspect-term representation.
3 days ago
arXiv

Syntax-Enhanced Self-Attention-Based Semantic Role Labeling

We present different approaches of encoding the syntactic information derived from dependency trees of different quality and representations; we propose a syntax-enhanced self-attention model and compare it with other two strong baseline methods; and we conduct experiments with newly published deep contextualized word representations...
1 day ago
arXiv

Self-Attention for Raw Optical Satellite Time Series Classification

Today, self-attention based neural networks dominate the state-of-the-art in natural language processing but are hardly explored and tested in the remote sensing context.
3 days ago
arXiv

### optimization problems

5 preprints

Solving Dynamic Multi-objective Optimization Problems Using Incremental Support Vector Machine

The main feature of the Dynamic Multi-objective Optimization Problems (DMOPs) is that optimization objective functions will change with times or environments.
7 days ago
arXiv

Single Versus Union: Non-parallel Support Vector Machine Frameworks

It solves a series of small optimization problems to obtain a series of hyperplanes, but is hard to measure the loss of each sample.
5 days ago
arXiv

S-DIGing: A Stochastic Gradient Tracking Algorithm for Distributed Optimization

The intention of this work is to solve large-scale optimization problems where the local objective function is complicated and numerous.
7 days ago
arXiv

### data collection

5 preprints

Multi-UAV Data Collection Framework for Wireless Sensor Networks

In this paper, we propose a framework design for wireless sensor networks based on multiple unmanned aerial vehicles (UAVs).
3 days ago
arXiv

Design and Implementation of a Wireless SensorNetwork for Agricultural Applications

The almost static nature of wireless links in the farm motivated us to use the same tree for a long data collection period(3 days).
4 days ago
arXiv

Maximum Lifetime Convergecast Tree in Wireless Sensor Networks

The energy consumption of different nodes under the proposed algorithm are shown to be more balanced than under the shortest path tree and random data collection tree algorithms.
4 days ago
arXiv

### proposed algorithm

5 preprints

Distributed voting in beep model

The proposed algorithms have a termination detection procedure to check whether voting is achieved.
4 days ago
arXiv

Maximum Lifetime Convergecast Tree in Wireless Sensor Networks

Hence, the proposed algorithm provides a higher network lifetime than that under the other two algorithms.
4 days ago
arXiv

Frequency Diverse Array Radar: New Results and Discrete Fourier Transform Based Beampattern

Simulation results compare the performance of our proposed algorithm with the existing ones and show the superiority of our proposed algorithm.
5 days ago
arXiv

### natural language

4 preprints

Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight

We evaluate our approach on a natural language instruction-following task with a physical quadcopter, and demonstrate effective execution and exploration behavior.
5 days ago
arXiv

Byte-Pair Encoding for Text-to-SQL Generation

The Byte-Pair Encoding algorithm (BPE) has previously been used to improve machine translation (MT) between natural languages.
6 days ago
arXiv

GF + MMT = GLF -- From Language to Semantics through LF

GF is a tool for syntactic analysis, generation, and translation with complex natural language grammars and MMT can be used to specify logical systems and to represent knowledge in them.
3 days ago
arXiv

### monte carlo

4 preprints

A quasi-Monte Carlo Method for an Optimal Control Problem Under Uncertainty

The overall discretization error of the problem, consisting of the dimension truncation error, finite element discretization error and quasi-Monte Carlo quadrature error, is derived in detail.
4 days ago
arXiv

Another look at the treatment of data uncertainty in Markov chain Monte Carlo inversion and other probabilistic methods

In a synthetic test, the proposed mixed measurement error distribution allows recovery of the underlying model even in the presence of 6\% outliers, which completely destroy the ability of a regular Markov chain Monte Carlo or linear search to provide a meaningful image.
1 day ago
EarthArXiv

GPU-accelerated mesh-based Monte Carlo photon transport simulations

The mesh-based Monte Carlo (MMC) algorithm is increasingly used as the gold-standard for developing new biophotonics modeling techniques in 3-D complex tissues, including both diffusion-based and various Monte Carlo (MC) based methods.
4 days ago
bioRxiv

### convolutional networks

4 preprints

Facial Expression Restoration Based on Improved Graph Convolutional Networks

Unlike conventional graph convolutional networks taking vectors as input features, IGCN can use tensors of face patches as inputs.
3 days ago
arXiv

Selective Attention Based Graph Convolutional Networks for Aspect-Level Sentiment Classification

In this paper, we propose to employ graph convolutional networks (GCNs) on the dependency tree to learn syntax-aware representations of aspect terms.
3 days ago
arXiv

Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection

This paper proposes an end-to-end deep learning framework for facial AU detection with graph convolutional network (GCN) for AU relation modeling, which has not been explored before.
4 days ago
arXiv

### sequence to sequence

4 preprints

Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer

We propose a sequence-to-sequence singing synthesizer, which avoids the need for training data with pre-aligned phonetic and acoustic features.
4 days ago
arXiv

Building Dynamic Knowledge Graphs from Text-based Games

In this preliminary work, we propose a novel Sequence-to-Sequence (Seq2Seq) architecture to generate elementary KG operations.
5 days ago
arXiv

XL-Editor: Post-editing Sentences with XLNet

Concretely, XL-Editor can (1) estimate the probability of inserting a variable-length sequence into a specific position of a given sentence; (2) execute post-editing operations such as insertion, deletion, and replacement based on the estimated variable-length insertion probability; (3) complement existing sequence-to-sequence models...
7 days ago
arXiv

### finite element

3 preprints

Using exact geometry information in finite element computations

Our study shows that all geometry needs inside the simulators can be satisfied by just two primitives'': elementary queries posed by the simulation software to the geometry description.
4 days ago
arXiv

Finite Element Methods for Maxwell's Equations

For the conforming edge finite element methods, such estimates allow, at least, piecewise smooth coefficients.
4 days ago
arXiv

Finite Element Error Analysis of Surface Stokes Equations in Stream Function Formulation

We consider a surface Stokes problem in stream function formulation on a simply connected oriented surface $\Gamma \subset \mathbb{R}^3$ without boundary.
5 days ago
arXiv

### array sets

2 preprints

New Construction of Complementary Sequence (or Array) Sets and Complete Complementary Codes (II)

Previously, we have presented a framework to use the para-unitary (PU) matrix-based approach for constructing new complementary sequence set (CSS), complete complementary code (CCC), complementary sequence array (CSA), and complete complementary array (CCA).
4 days ago
arXiv

New Construction of Complementary Sequence (or Array) Sets and Complete Complementary Codes (I)

A new method to construct $q$-ary complementary sequence (or array) sets (CSSs) and complete complementary codes (CCCs) of size $N$ is introduced in this paper.
4 days ago
arXiv

### construction of complementary sequence

2 preprints

New Construction of Complementary Sequence (or Array) Sets and Complete Complementary Codes (I)

A new method to construct $q$-ary complementary sequence (or array) sets (CSSs) and complete complementary codes (CCCs) of size $N$ is introduced in this paper.
4 days ago
arXiv

New Construction of Complementary Sequence (or Array) Sets and Complete Complementary Codes (II)

Previously, we have presented a framework to use the para-unitary (PU) matrix-based approach for constructing new complementary sequence set (CSS), complete complementary code (CCC), complementary sequence array (CSA), and complete complementary array (CCA).
4 days ago
arXiv