## last week in computer science

## 594

new preprints about computer science in the last week## arXiv

most active server in computer science in the last week#### most popular topics mentioned by preprints

### state of the art

34 preprintsZero-Shot Multi-Speaker Text-To-Speech with **State**-of-the-**art** Neural
Speaker Embeddings

**the**effects of different types

**of**

**state**-of-the-

**art**neural speaker embeddings on speaker similarity for unseen speakers.

arXiv

Self-Attention for Raw Optical Satellite Time Series Classification

**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).

arXiv

Stain Style Transfer using Transitive Adversarial Networks

**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.

arXiv

### neural networks

27 preprintsVanishing Nodes: Another Phenomenon That Makes Training Deep **Neural**
**Networks** Difficult

**neural**

**networks**.

arXiv

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

**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...

arXiv

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

**neural**

**networks**; rather, our results show that some classes of neural

**network**architectures naturally encode the physics contained in some HJ PDEs.

arXiv

### deep learning

21 preprintsApplying **deep** **learning** to teleseismic phase detection and picking: PcP
and PKiKP cases

**deep**-learning-based scheme.

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.

bioRxiv

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

**Deep**Prog are predictive of the subtypes of some other cancers, demonstrating the utility of DeepProg for transfer

**learning**.

medRxiv

### machine learning

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

**machine**

**learning**classifier with greater than 80 percent predictive precision.

arXiv

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

**machine**

**learning**metaphysical result was observed by the omission of CO2 concentrations as an input variable.

EarthArXiv

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

**learning**and

**machine**-learning models.

medRxiv

### reinforcement learning

10 preprintsDealing with Sparse Rewards in **Reinforcement** **Learning**

**reinforcement**

**learning**solution, by combining aspects of two existing state of the art sparse reward solutions.

arXiv

Robust Model Predictive Shielding for Safe **Reinforcement** **Learning** with
Stochastic Dynamics

**reinforcement**

**learning**, e.g., in a simulated environment.

arXiv

Reciprocal Collision Avoidance for General Nonlinear Agents using
**Reinforcement** **Learning**

**reinforcement**

**learning**(RL).

arXiv

### experiments show

8 preprintsVanishing Nodes: Another Phenomenon That Makes Training Deep Neural Networks Difficult

**experiments**

**show**that the likelihood of failed training increases as the depth of the network increases.

arXiv

Inheritance without reactivation: Insights from crustal-scale analogue **experiments**

**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.

EarthArXiv

Contextual Prediction Difference Analysis

**experiments**

**show**the superiority of our method by explaining image classifications of the state-of-the-art deep convolutional neural networks.

arXiv

### based approach

7 preprintsStudy of the impact of climate change on precipitation in Paris area
using method **based** on iterative multiscale dynamic time warping (IMS-DTW)

**based**

**approach**.

arXiv

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

**based**inverse problem

**approach**es for other settings, where fully-sampled data is not available or possible to acquire.

arXiv

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

**based**

**approach**.

arXiv

### proposed approach

7 preprintsA Hybrid Semantic Parsing **Approach** for Tabular Data Analysis

**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...

arXiv

Bayesian nonparametric temporal dynamic clustering via autoregressive Dirichlet priors

**proposed**

**approach**include flexibility in applications, ease of computations and interpretability.

arXiv

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

**proposed**

**approach**clearly outperforms a recently published method in terms of accuracy.

arXiv

### generative adversarial

7 preprintsAssessment of **Generative** **Adversarial** Networks Model for Synthetic
Optical Coherence Tomography Images of Retinal Disorders

**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).

arXiv

Image Difficulty Curriculum for **Generative** **Adversarial** Networks (CuGAN)

**Generative**

**Adversarial**Networks (GANs) are still notoriously hard to train.

arXiv

Facial Expression Restoration Based on Improved Graph Convolutional Networks

**generative**

**adversarial**network by integrating an improved graph convolutional network (IGCN) and region relation modeling block (RRMB).

arXiv

### training data

7 preprintsCoercing Machine Learning to Output Physically Accurate Results

**trained**to simply be interpolation functions that map input variables to output values interpolated from the

**training**

**data**in a linear/nonlinear fashion.

arXiv

Semantic Segmentation of Skin Lesions using a Small **Data** Set

**data**should be cropped to reduce complexity and augmented during

**training**to reduce the likelihood of overfitting.

arXiv

Region Based Adversarial Synthesis of Facial Action Units

**datas**et to verify the effectiveness of our proposed AU synthesis method.

arXiv

### state of the art performance

6 preprintsDeepSeqPanII: 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.

bioRxiv

Inception Capsule Network for Retinal Blood Vessel Segmentation and Centerline Extraction

**state**-of-the-

**art**

**performance**for vessel segmentation and outperformed existing methods for centerline extraction.

bioRxiv

An Adaptive Empirical Bayesian Method for Sparse Deep Learning

**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.

arXiv

### numerical experiments

6 preprintsFinite Element Error Analysis of Surface Stokes Equations in Stream Function Formulation

arXiv

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

**numerical**

**experiments**to verify the efficiency of the schemes and to...

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.

arXiv

### data analysis

5 preprintsA Hybrid Semantic Parsing Approach for Tabular **Data** **Analysis**

**datas**et for more complex queries in both English and Chinese, which demonstrates our language expansion and quick-start ability.

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.

PsyArXiv

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

**data**

**analysis**may be complicated by the constraint on the number of clusters in treatment and control.

NBER

### graph convolutional

5 preprintsFacial Expression Restoration Based on Improved **Graph** **Convolutional**
Networks

**graph**

**convolutional**networks taking vectors as input features, IGCN can use tensors of face patches as inputs.

arXiv

Relation Modeling with **Graph** **Convolutional** Networks for Facial Action
Unit Detection

**graph**

**convolutional**network (GCN) for AU relation modeling, which has not been explored before.

arXiv

Semantic **Graph** **Convolutional** Network for Implicit Discourse Relation
Classification

**Graph**

**Convolutional**Network (SGCN) to enhance the modeling of inter-argument semantics on a deeper interaction level for implicit discourse relation classification.

arXiv

### attention based

5 preprintsSelective **Attention** **Based** Graph Convolutional Networks for Aspect-Level
Sentiment Classification

**attention**

**based**GCN block (SA-GCN) to find the most important context words, and directly aggregate these information into the aspect-term representation.

arXiv

Syntax-Enhanced Self-Attention-**Based** Semantic Role Labeling

**attention**model and compare it with other two strong baseline methods; and we conduct experiments with newly published deep contextualized word representations...

arXiv

Self-**Attention** for Raw Optical Satellite Time Series Classification

**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.

arXiv

### optimization problems

5 preprintsSolving Dynamic Multi-objective **Optimization** **Problems** Using Incremental
Support Vector Machine

**Optimization**

**Problems**(DMOPs) is that optimization objective functions will change with times or environments.

arXiv

Single Versus Union: Non-parallel Support Vector Machine Frameworks

**optimization**

**problems**to obtain a series of hyperplanes, but is hard to measure the loss of each sample.

arXiv

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

**optimization**

**problems**where the local objective function is complicated and numerous.

arXiv

### data collection

5 preprintsMulti-UAV **Data** **Collection** Framework for Wireless Sensor Networks

arXiv

Design and Implementation of a Wireless SensorNetwork for Agricultural Applications

**data**

**collection**period(3 days).

arXiv

Maximum Lifetime Convergecast Tree in Wireless Sensor Networks

**data**

**collection**tree algorithms.

arXiv

### proposed algorithm

5 preprintsDistributed voting in beep model

**proposed**

**algorithms**have a termination detection procedure to check whether voting is achieved.

arXiv

Maximum Lifetime Convergecast Tree in Wireless Sensor Networks

**proposed**

**algorithm**provides a higher network lifetime than that under the other two

**algorithms**.

arXiv

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

**proposed**

**algorithm**with the existing ones and show the superiority of our proposed algorithm.

arXiv

### natural language

4 preprintsLearning to Map **Natural** **Language** Instructions to Physical Quadcopter
Control using Simulated Flight

**natural**

**language**instruction-following task with a physical quadcopter, and demonstrate effective execution and exploration behavior.

arXiv

Byte-Pair Encoding for Text-to-SQL Generation

**natural**

**languages**.

arXiv

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

**natural**

**language**grammars and MMT can be used to specify logical systems and to represent knowledge in them.

arXiv

### monte carlo

4 preprintsA quasi-**Monte** **Carlo** Method for an Optimal Control Problem Under
Uncertainty

**Monte**

**Carlo**quadrature error, is derived in detail.

arXiv

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

**Monte**

**Carlo**or linear search to provide a meaningful image.

EarthArXiv

GPU-accelerated mesh-based **Monte** **Carlo** photon transport simulations

**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.

bioRxiv

### convolutional networks

4 preprintsFacial Expression Restoration Based on Improved Graph **Convolutional**
**Networks**

**convolutional**

**networks**taking vectors as input features, IGCN can use tensors of face patches as inputs.

arXiv

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

**convolutional**

**networks**(GCNs) on the dependency tree to learn syntax-aware representations of aspect terms.

arXiv

Relation Modeling with Graph **Convolutional** **Networks** for Facial Action
Unit Detection

**convolutional**

**network**(GCN) for AU relation modeling, which has not been explored before.

arXiv

### sequence to sequence

4 preprintsSequence-to-**sequence** Singing Synthesis Using the Feed-forward
Transformer

**sequence**singing synthesizer, which avoids the need for training data with pre-aligned phonetic and acoustic features.

arXiv

Building Dynamic Knowledge Graphs from Text-based Games

**Sequence**(Seq2Seq) architecture

**to**generate elementary KG operations.

arXiv

XL-Editor: Post-editing Sentences with XLNet

**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...

arXiv

### finite element

3 preprintsUsing exact geometry information in **finite** **element** computations

**elementary**queries posed by the simulation software to the geometry description.

arXiv

**Finite** **Element** Methods for Maxwell's Equations

**finite**

**element**methods, such estimates allow, at least, piecewise smooth coefficients.

arXiv

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

arXiv

### array sets

2 preprintsNew Construction of Complementary Sequence (or **Array**) **Sets** and Complete
Complementary Codes (II)

arXiv

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

arXiv

### construction of complementary sequence

2 preprintsNew **Construction** **of** **Complementary** **Sequence** (or Array) Sets and Complete
Complementary Codes (I)

arXiv

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

arXiv