scholarly journals SCFont: Structure-Guided Chinese Font Generation via Deep Stacked Networks

2019 ◽  
Vol 33 ◽  
pp. 4015-4022 ◽  
Author(s):  
Yue Jiang ◽  
Zhouhui Lian ◽  
Yingmin Tang ◽  
Jianguo Xiao
Keyword(s):  
Deep Learning ◽  
Domain Knowledge ◽  
State Of The Art ◽  
Automatic Generation ◽  
Chinese Characters ◽  
Generation System ◽  
Model Learning ◽  
High Quality ◽  
Large Numbers ◽  
Quantitative Assessments

Automatic generation of Chinese fonts that consist of large numbers of glyphs with complicated structures is now still a challenging and ongoing problem in areas of AI and Computer Graphics (CG). Traditional CG-based methods typically rely heavily on manual interventions, while recentlypopularized deep learning-based end-to-end approaches often obtain synthesis results with incorrect structures and/or serious artifacts. To address those problems, this paper proposes a structure-guided Chinese font generation system, SCFont, by using deep stacked networks. The key idea is to integrate the domain knowledge of Chinese characters with deep generative networks to ensure that high-quality glyphs with correct structures can be synthesized. More specifically, we first apply a CNN model to learn how to transfer the writing trajectories with separated strokes in the reference font style into those in the target style. Then, we train another CNN model learning how to recover shape details on the contour for synthesized writing trajectories. Experimental results validate the superiority of the proposed SCFont compared to the state of the art in both visual and quantitative assessments.

scholarly journals Unsupervised Deep Learning via Affinity Diffusion

2020 ◽  
Vol 34 (07) ◽  
pp. 11029-11036
Author(s):  
Jiabo Huang ◽  
Qi Dong ◽  
Shaogang Gong ◽  
Xiatian Zhu
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
General Purpose ◽  
Training Data ◽  
Learning Approach ◽  
Model Learning ◽  
Feature Representations ◽  
Discriminative Feature ◽  
Training Samples ◽  
Unsupervised Deep Learning

Convolutional neural networks (CNNs) have achieved unprecedented success in a variety of computer vision tasks. However, they usually rely on supervised model learning with the need for massive labelled training data, limiting dramatically their usability and deployability in real-world scenarios without any labelling budget. In this work, we introduce a general-purpose unsupervised deep learning approach to deriving discriminative feature representations. It is based on self-discovering semantically consistent groups of unlabelled training samples with the same class concepts through a progressive affinity diffusion process. Extensive experiments on object image classification and clustering show the performance superiority of the proposed method over the state-of-the-art unsupervised learning models using six common image recognition benchmarks including MNIST, SVHN, STL10, CIFAR10, CIFAR100 and ImageNet.

A self-learning finite element extraction system based on reinforcement learning

2021 ◽  
pp. 1-29
Author(s):  
Jie Pan ◽  
Jingwei Huang ◽  
Yunli Wang ◽  
Gengdong Cheng ◽  
Yong Zeng
Keyword(s):  
Reinforcement Learning ◽  
Mesh Generation ◽  
Domain Knowledge ◽  
Domain Boundary ◽  
Automatic Generation ◽  
Extraction System ◽  
Generation Process ◽  
High Quality ◽  
Geometric Boundary ◽  
Self Learning

Abstract Automatic generation of high-quality meshes is a base of CAD/CAE systems. The element extraction is a major mesh generation method for its capabilities to generate high-quality meshes around the domain boundary and to control local mesh densities. However, its widespread applications have been inhibited by the difficulties in generating satisfactory meshes in the interior of a domain or even in generating a complete mesh. The element extraction method's primary challenge is to define element extraction rules for achieving high-quality meshes in both the boundary and the interior of a geometric domain with complex shapes. This paper presents a self-learning element extraction system, FreeMesh-S, that can automatically acquire robust and high-quality element extraction rules. Two central components enable the FreeMesh-S: (1) three primitive structures of element extraction rules, which are constructed according to boundary patterns of any geometric boundary shapes; (2) a novel self-learning schema, which is used to automatically define and refine the relationships between the parameters included in the element extraction rules, by combining an Advantage Actor-Critic (A2C) reinforcement learning network and a Feedforward Neural Network (FNN). The A2C network learns the mesh generation process through random mesh element extraction actions using element quality as a reward signal and produces high-quality elements over time. The FNN takes the mesh generated from the A2C as samples to train itself for the fast generation of high-quality elements. FreeMesh-S is demonstrated by its application to two-dimensional quad mesh generation. The meshing performance of FreeMesh-S is compared with three existing popular approaches on ten pre-defined domain boundaries. The experimental results show that even with much less domain knowledge required to develop the algorithm, FreeMesh-S outperforms those three approaches in essential indices. FreeMesh-S significantly reduces the time and expertise needed to create high-quality mesh generation algorithms.

scholarly journals DGA CapsNet: 1D Application of Capsule Networks to DGA Detection

Information ◽  
2019 ◽  
Vol 10 (5) ◽  
pp. 157 ◽  
Author(s):  
Daniel S. Berman
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Real Time ◽  
Convolutional Neural Networks ◽  
Recurrent Neural Networks ◽  
State Of The Art ◽  
One Dimensional ◽  
Domain Names ◽  
Large Numbers ◽  
And Control

Domain generation algorithms (DGAs) represent a class of malware used to generate large numbers of new domain names to achieve command-and-control (C2) communication between the malware program and its C2 server to avoid detection by cybersecurity measures. Deep learning has proven successful in serving as a mechanism to implement real-time DGA detection, specifically through the use of recurrent neural networks (RNNs) and convolutional neural networks (CNNs). This paper compares several state-of-the-art deep-learning implementations of DGA detection found in the literature with two novel models: a deeper CNN model and a one-dimensional (1D) Capsule Networks (CapsNet) model. The comparison shows that the 1D CapsNet model performs as well as the best-performing model from the literature.

scholarly journals RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach

2016 ◽  
Author(s):  
Xiaoyong Pan ◽  
Hong-Bin Shen
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Binding Sites ◽  
Domain Knowledge ◽  
Large Scale ◽  
Knowledge Integration ◽  
State Of The Art ◽  
Binding Motifs ◽  
Abstraction Level ◽  
Cross Domain

AbstractBackgroundRNAs play key roles in cells through the interactions with proteins known as the RNA-binding proteins (RBP) and their binding motifs enable crucial understanding of the post-transcriptional regulation of RNAs. How the RBPs correctly recognize the target RNAs and why they bind specific positions is still far from clear. Machine learning-based algorithms are widely acknowledged to be capable of speeding up this process. Although many automatic tools have been developed to predict the RNA-protein binding sites from the rapidly growing multi-resource data, e.g. sequence, structure, their domain specific features and formats have posed significant computational challenges. One of current difficulties is that the cross-source shared common knowledge is at a higher abstraction level beyond the observed data, resulting in a low efficiency of direct integration of observed data across domains. The other difficulty is how to interpret the prediction results. Existing approaches tend to terminate after outputting the potential discrete binding sites on the sequences, but how to assemble them into the meaningful binding motifs is a topic worth of further investigation.ResultsIn viewing of these challenges, we propose a deep learning-based framework (iDeep) by using a novel hybrid convolutional neural network and deep belief network to predict the RBP interaction sites and motifs on RNAs. This new protocol is featured by transforming the original observed data into a high-level abstraction feature space using multiple layers of learning blocks, where the shared representations across different domains are integrated. To validate our iDeep method, we performed experiments on 31 large-scale CLIP-seq datasets, and our results show that by integrating multiple sources of data, the average AUC can be improved by 8% compared to the best single-source-based predictor; and through cross-domain knowledge integration at an abstraction level, it outperforms the state-of-the-art predictors by 6%. Besides the overall enhanced prediction performance, the convolutional neural network module embedded in iDeep is also able to automatically capture the interpretable binding motifs for RBPs. Large-scale experiments demonstrate that these mined binding motifs agree well with the experimentally verified results, suggesting iDeep is a promising approach in the real-world applications.ConclusionThe iDeep framework not only can achieve promising performance than the state-of-the-art predictors, but also easily capture interpretable binding motifs. iDeep is available at http://www.csbio.sjtu.edu.cn/bioinf/iDeep

scholarly journals Generative-Discriminative Complementary Learning

2020 ◽  
Vol 34 (04) ◽  
pp. 6526-6533
Author(s):  
Yanwu Xu ◽  
Mingming Gong ◽  
Junxiang Chen ◽  
Tongliang Liu ◽  
Kun Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Conditional Distribution ◽  
State Of The Art ◽  
Empirical Studies ◽  
Learning Method ◽  
Learning Problem ◽  
High Quality ◽  
Learning Methods ◽  
Weak Supervision

The majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases. In this paper, we study the complementary learning problem. Unlike ordinary labels, complementary labels are easy to obtain because an annotator only needs to provide a yes/no answer to a randomly chosen candidate class for each instance. We propose a generative-discriminative complementary learning method that estimates the ordinary labels by modeling both the conditional (discriminative) and instance (generative) distributions. Our method, we call Complementary Conditional GAN (CCGAN), improves the accuracy of predicting ordinary labels and is able to generate high-quality instances in spite of weak supervision. In addition to the extensive empirical studies, we also theoretically show that our model can retrieve the true conditional distribution from the complementarily-labeled data.

scholarly journals TableRobot: an automatic annotation method for heterogeneous tables

2021 ◽  
Author(s):  
Guibin Wu ◽  
Junjie Zhou ◽  
Yongping Xiong ◽  
Chaoyi Zhou ◽  
Chong Li
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
State Of The Art ◽  
Automatic Annotation ◽  
Learning Networks ◽  
High Quality ◽  
Annotation Method ◽  
Table Recognition ◽  
Annotation Data ◽  
Optimum Solution

AbstractUsing deep learning networks to recognize the table attracts lots of attention. However, due to the lack of high-quality table datasets, the performance of using deep learning networks is limited. Therefore, TableRobot has been proposed, an automatic annotation method for heterogeneous tables. To be more specific, the annotations of table consist of the coordinates of the item block and the mapping relationship between item blocks and table cells. In order to transform the task, we successfully design an algorithm based on the greedy approach to find the optimum solution. To evaluate the performance of TableRobot, we check the annotation data of 3000 tables collected from the LaTex documents in arXiv.com, and the result shows that TableRobot can generate table annotation datasets with the accuracy of 93.2%. Besides, the table annotation data is feed into GraphTSR which is a state-of-the-art table recognition graph neural network, and the F1 value of the network has increased by nearly 10% compared with before.

Automatic generation of a large dictionary with concreteness/abstractness ratings based on a small human dictionary

2021 ◽  
pp. 1-9
Author(s):  
Vladimir Ivanov ◽  
Valery Solovyev
Keyword(s):  
State Of The Art ◽  
Research Question ◽  
Automatic Generation ◽  
Expert Assessment ◽  
High Quality ◽  
Test Set ◽  
Expert Assessments ◽  
Abstract Words ◽  
Expert Ratings

Concrete/abstract words are used in a growing number of psychological and neurophysiological research. For a few languages, large dictionaries have been created manually. This is a very time-consuming and costly process. To generate large high-quality dictionaries of concrete/abstract words automatically one needs extrapolating the expert assessments obtained on smaller samples. The research question that arises is how small such samples should be to do a good enough extrapolation. In this paper, we present a method for automatic ranking concreteness of words and propose an approach to significantly decrease amount of expert assessment. The method has been evaluated on a large test set for English. The quality of the constructed dictionaries is comparable to the expert ones. The correlation between predicted and expert ratings is higher comparing to the state-of-the-art methods.

scholarly journals MINDWALC: mining interpretable, discriminative walks for classification of nodes in a knowledge graph

2020 ◽  
Vol 20 (S4) ◽  
Author(s):  
Gilles Vandewiele ◽  
Bram Steenwinckel ◽  
Filip De Turck ◽  
Femke Ongenae
Keyword(s):  
Deep Learning ◽  
Domain Knowledge ◽  
State Of The Art ◽  
Predictive Performance ◽  
Expressive Power ◽  
Black Box ◽  
Knowledge Graph ◽  
Numerical Representation ◽  
Mining Algorithm ◽  
Knowledge Graphs

Abstract Background Leveraging graphs for machine learning tasks can result in more expressive power as extra information is added to the data by explicitly encoding relations between entities. Knowledge graphs are multi-relational, directed graph representations of domain knowledge. Recently, deep learning-based techniques have been gaining a lot of popularity. They can directly process these type of graphs or learn a low-dimensional numerical representation. While it has been shown empirically that these techniques achieve excellent predictive performances, they lack interpretability. This is of vital importance in applications situated in critical domains, such as health care. Methods We present a technique that mines interpretable walks from knowledge graphs that are very informative for a certain classification problem. The walks themselves are of a specific format to allow for the creation of data structures that result in very efficient mining. We combine this mining algorithm with three different approaches in order to classify nodes within a graph. Each of these approaches excels on different dimensions such as explainability, predictive performance and computational runtime. Results We compare our techniques to well-known state-of-the-art black-box alternatives on four benchmark knowledge graph data sets. Results show that our three presented approaches in combination with the proposed mining algorithm are at least competitive to the black-box alternatives, even often outperforming them, while being interpretable. Conclusions The mining of walks is an interesting alternative for node classification in knowledge graphs. Opposed to the current state-of-the-art that uses deep learning techniques, it results in inherently interpretable or transparent models without a sacrifice in terms of predictive performance.

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

Sign in / Sign up

Export Citation Format

Share Document