scholarly journals Automatic comment generation for source code using external information by neural networks for computational thinking

2020 ◽  
Vol 4 (2) ◽  
pp. 39-61
Author(s):  
Hiromitsu Shiina ◽  
Sakuei Onishi ◽  
Akiyoshi Takahashi ◽  
Nobuyuki Kobayashi
Keyword(s):  
Neural Networks ◽  
Source Code ◽  
Computational Thinking ◽  
External Information

scholarly journals An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos

2020 ◽  
Vol 34 (01) ◽  
pp. 303-311 ◽  
Author(s):  
Sicheng Zhao ◽  
Yunsheng Ma ◽  
Yang Gu ◽  
Jufeng Yang ◽  
Tengfei Xing ◽  
...  
Keyword(s):  
Neural Networks ◽  
Emotion Recognition ◽  
State Of The Art ◽  
Source Code ◽  
Cross Entropy ◽  
Attention Network ◽  
Audio Features ◽  
End To End ◽  
3D Cnn ◽  
And Training

Emotion recognition in user-generated videos plays an important role in human-centered computing. Existing methods mainly employ traditional two-stage shallow pipeline, i.e. extracting visual and/or audio features and training classifiers. In this paper, we propose to recognize video emotions in an end-to-end manner based on convolutional neural networks (CNNs). Specifically, we develop a deep Visual-Audio Attention Network (VAANet), a novel architecture that integrates spatial, channel-wise, and temporal attentions into a visual 3D CNN and temporal attentions into an audio 2D CNN. Further, we design a special classification loss, i.e. polarity-consistent cross-entropy loss, based on the polarity-emotion hierarchy constraint to guide the attention generation. Extensive experiments conducted on the challenging VideoEmotion-8 and Ekman-6 datasets demonstrate that the proposed VAANet outperforms the state-of-the-art approaches for video emotion recognition. Our source code is released at: https://github.com/maysonma/VAANet.

scholarly journals A Deep Neural Networks Approach for Augmenting Samples of Land Cover Classification

Land ◽  
2020 ◽  
Vol 9 (8) ◽  
pp. 271
Author(s):  
Chuanpeng Zhao ◽  
Yaohuan Huang
Keyword(s):  
Neural Networks ◽  
Land Cover ◽  
Deep Neural Networks ◽  
Anthropogenic Activities ◽  
Remote Sensing Data ◽  
Label Propagation ◽  
External Information ◽  
Image Objects ◽  
Error Accumulation ◽  
Land Cover Maps

Land cover is one of key indicators for modeling ecological, environmental, and climatic processes, which changes frequently due to natural factors and anthropogenic activities. The changes demand various samples for updating land cover maps, although in reality the number of samples is always insufficient. Sample augment methods can fill this gap, but these methods still face difficulties, especially for high-resolution remote sensing data. The difficulties include the following: (1) excessive human involvement, which is mostly caused by human interpretation, even by active learning-based methods; (2) large variations of segmented land cover objects, which affects the generalization to unseen areas especially for proposed methods that are validated in small study areas. To solve these problems, we proposed a sample augment method incorporating the deep neural networks using a Gaofen-2 image. To avoid error accumulation, the neural network-based sample augment (NNSA) framework employs non-iterative procedure, and augments from 184 image objects with labels to 75,112 samples. The overall accuracy (OA) of NNSA is 20% higher than that of label propagation (LP) in reference to expert interpreted results; the LP has an OA of 61.16%. The accuracy decreases by approximately 10% in the coastal validation area, which has different characteristics from the inland samples. We also compared the iterative and non-iterative strategies without external information added. The results of the validation area containing original samples show that non-iterative methods have a higher OA and a lower sample imbalance. The NNSA method that augments sample size with higher accuracy can benefit the update of land cover information.

scholarly journals MASKS: A Multi-Artificial Neural Networks System's verification approach

2020 ◽  
Author(s):  
Amirhoshang Hoseinpour Dehkordi ◽  
Majid Alizadeh ◽  
Ebrahim Ardeshir-Larijani ◽  
Ali Movaghar
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Special Property ◽  
External Information ◽  
Multi Agent Systems ◽  
Classification Problems ◽  
Multi Agent ◽  
Artificial Neural

<div>Artificial Neural networks are one of the most widely applied approaches for classification problems. However, developing an errorless artificial neural network is in practice impossible, due to the statistical nature of such networks. The employment of artificial neural networks in critical applications has rendered any such emerging errors, in these systems, incredibly more significant. Nevertheless, the real consequences of such errors have not been addressed, especially due to lacking verification approaches. This study aims to develop a verification method that eliminates errors through the integration of multiple artificial neural networks. In order to do this, first of all, a special property has been defined, by the authors, to extract the knowledge of these artificial neural networks. </div><div>Furthermore, a multi-agent system has been designed, itself comprised of multiple artificial neural networks, in order to check whether the aforementioned special property has been satisfied, or not. Also, in order to help examine the reasoning concerning the aggregation of the distributed knowledge, itself gained through the combined effort of separate artificial neural networks and acquired external information sources, a dynamic epistemic logic-based method has been proposed.</div><div>Finally, we believe aggregated knowledge may lead to self-awareness for the system. As a result, our model shall be capable of verifying specific inputs, if the cumulative knowledge of the entire system proves its correctness. </div><div>In conclusion, and formulated for multi-agent systems, a knowledge-sharing algorithm (Abbr. MASKS) has been developed. Which after being applied on the MNIST dataset successfully reduced the error rate to roughly one-eighth of previous runs on individual artificial neural network in the same model. </div>

scholarly journals Integrating Relation Constraints with Neural Relation Extractors

2020 ◽  
Vol 34 (05) ◽  
pp. 9442-9449
Author(s):  
Yuan Ye ◽  
Yansong Feng ◽  
Bingfeng Luo ◽  
Yuxuan Lai ◽  
Dongyan Zhao
Keyword(s):  
Neural Networks ◽  
Source Code ◽  
Relation Extraction ◽  
Rapid Progress ◽  
Post Processing ◽  
Unified Framework ◽  
Loss Term

Recent years have seen rapid progress in identifying predefined relationship between entity pairs using neural networks (NNs). However, such models often make predictions for each entity pair individually, thus often fail to solve the inconsistency among different predictions, which can be characterized by discrete relation constraints. These constraints are often defined over combinations of entity-relation-entity triples, since there often lack of explicitly well-defined type and cardinality requirements for the relations. In this paper, we propose a unified framework to integrate relation constraints with NNs by introducing a new loss term, Constraint Loss. Particularly, we develop two efficient methods to capture how well the local predictions from multiple instance pairs satisfy the relation constraints. Experiments on both English and Chinese datasets show that our approach can help NNs learn from discrete relation constraints to reduce inconsistency among local predictions, and outperform popular neural relation extraction (NRE) models even enhanced with extra post-processing. Our source code and datasets will be released at https://github.com/PKUYeYuan/Constraint-Loss-AAAI-2020.

scholarly journals Megatrend and Intervention Impact Analyzer for Jobs: A Visualization Method for Labor Market Intelligence

2018 ◽  
Vol 34 (4) ◽  
pp. 961-979
Author(s):  
Rain Opik ◽  
Toomas Kirt ◽  
Innar Liiv
Keyword(s):  
Labor Market ◽  
Source Code ◽  
Heterogeneous Data ◽  
External Information ◽  
Market Intelligence ◽  
Heterogeneous Data Sources ◽  
Prototype Tool ◽  
Intervention Impact ◽  
The Impact

Abstract This article presents a visual method for representing the complex labor market internal structure from the perspective of similar occupations based on shared skills; and a prototype tool for interacting with the visualization, together with an extended description of graph construction and the necessary data processing for linking multiple heterogeneous data sources. Since the labor market is not an isolated phenomenon and is constantly impacted by external trends and interventions, the presented method is designed to enable adding extra layers of external information. For instance, what is the impact of a megatrend or an intervention on the labor market? Which parts of the labor market are the most vulnerable to an approaching megatrend or planned intervention? A case study analyzing the labor market together with the megatrend of job automation and computerization is presented. The source code of the prototype is released as open source for repeatability.

Chapter 4. Graph Reasoning Networks and Applications

2021 ◽  
Author(s):  
Qingxing Cao ◽  
Wentao Wan ◽  
Xiaodan Liang ◽  
Liang Lin
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Domain Knowledge ◽  
Feature Learning ◽  
External Information ◽  
Feature Representations ◽  
Domain Specific ◽  
The Neural Network ◽  
Structured Knowledge ◽  
Knowledge Graphs

Despite the significant success in various domains, the data-driven deep neural networks compromise the feature interpretability, lack the global reasoning capability, and can’t incorporate external information crucial for complicated real-world tasks. Since the structured knowledge can provide rich cues to record human observations and commonsense, it is thus desirable to bridge symbolic semantics with learned local feature representations. In this chapter, we review works that incorporate different domain knowledge into the intermediate feature representation.These methods firstly construct a domain-specific graph that represents related human knowledge. Then, they characterize node representations with neural network features and perform graph convolution to enhance these symbolic nodes via the graph neural network(GNN).Lastly, they map the enhanced node feature back into the neural network for further propagation or prediction. Through integrating knowledge graphs into neural networks, one can collaborate feature learning and graph reasoning with the same supervised loss function and achieve a more effective and interpretable way to introduce structure constraints.

Sign in / Sign up

Export Citation Format

Share Document