scholarly journals Global and Local Information Adjustment for Semantic Similarity Evaluation

2021 ◽  
Vol 11 (5) ◽  
pp. 2161
Author(s):  
Tak-Sung Heo ◽  
Jong-Dae Kim ◽  
Chan-Young Park ◽  
Yu-Seop Kim
Keyword(s):  
Neural Networks ◽  
Performance Improvement ◽  
Semantic Similarity ◽  
Local Information ◽  
Global Information ◽  
Weight Parameter ◽  
Proposed Model ◽  
Negative Effect ◽  
Global And Local ◽  
Question And Answering

Semantic similarity evaluation is used in various fields such as question-and-answering and plagiarism testing, and many studies have been conducted into this problem. In previous studies using neural networks to evaluate semantic similarity, similarity has been measured using global information of sentence pairs. However, since sentences do not only have one meaning but a variety of meanings, using only global information can have a negative effect on performance improvement. Therefore, in this study, we propose a model that uses global information and local information simultaneously to evaluate the semantic similarity of sentence pairs. The proposed model can adjust whether to focus more on global information or local information through a weight parameter. As a result of the experiment, the proposed model can show that the accuracy is higher than existing models that use only global information.

scholarly journals A Study of OWA Operators Learned in Convolutional Neural Networks

2021 ◽  
Vol 11 (16) ◽  
pp. 7195
Author(s):  
Iris Dominguez-Catena ◽  
Daniel Paternain ◽  
Mikel Galar
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Practical Method ◽  
Local Information ◽  
Weighted Averaging ◽  
Global Information ◽  
Owa Operator ◽  
Owa Operators ◽  
Ordered Weighted Averaging

Ordered Weighted Averaging (OWA) operators have been integrated in Convolutional Neural Networks (CNNs) for image classification through the OWA layer. This layer lets the CNN integrate global information about the image in the early stages, where most CNN architectures only allow for the exploitation of local information. As a side effect of this integration, the OWA layer becomes a practical method for the determination of OWA operator weights, which is usually a difficult task that complicates the integration of these operators in other fields. In this paper, we explore the weights learned for the OWA operators inside the OWA layer, characterizing them through their basic properties of orness and dispersion. We also compare them to some families of OWA operators, namely the Binomial OWA operator, the Stancu OWA operator and the exponential RIM OWA operator, finding examples that are currently impossible to generalize through these parameterizations.

Processing of global and local information in memory

1989 ◽  
Vol 41 (1) ◽  
pp. 167-181 ◽  
Author(s):  
Rino Rumiati ◽  
Roberto Nicoletti ◽  
Remo Job
Keyword(s):  
Local Level ◽  
Memory System ◽  
Local Information ◽  
Global Information ◽  
Global Level ◽  
Capital Letter ◽  
Global And Local

The experiments reported in this paper were designed to test how global and local information are processed by the memory system. When subjects are required to match a given letter with either a previously presented large capital letter or the small capital letters comprising it, (1) responses to the global level (i.e. the big letter) are faster than responses to the local level (i.e. the small letters), and (2) responses to the latter level only are affected by the consistency between the large and the small letters (Experiment 2), a pattern similar to that obtained in perception (Experiment 1). Such results obtain when subjects are required to attend to only one level with a short ISI between the first and second stimulus, but not when a longer ISI is used (Experiment 5) or when subjects are required to attend to both levels at the same time (Experiments 3 and 4). The results are discussed in the light of a model that postulates a temporal precedence of the global information over the local one at the perceptual level.

Novel Hybrid Neural Network for Dense Depth Estimation using On-Board Monocular Images

2020 ◽  
Vol 2674 (12) ◽  
pp. 312-323
Author(s):  
Shaocheng Jia ◽  
Xin Pei ◽  
Zi Yang ◽  
Shan Tian ◽  
Yun Yue
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Estimation Method ◽  
Depth Estimation ◽  
Local Information ◽  
Depth Information ◽  
Global Information ◽  
Hybrid Neural Network ◽  
Multi Scale ◽  
Feature Correlation

Depth information from still 2D images plays an important role in automated driving, driving safety, and robotics. Monocular depth estimation is considered as an ill-posed and inherently ambiguous problem in general, and a tight issue is how to obtain global information efficiently since pure convolutional neural networks (CNNs) merely extract the local information. To end that, some previous works utilized conditional random fields (CRFs) to obtain the global information, but it is notoriously difficult to optimize. In this paper, a novel hybrid neural network is proposed to solve that, and concurrently a dense depth map is predicted from the monocular still image. Specifically: first, the deep residual network is utilized to obtain multi-scale local information and then feature correlation (FCL) blocks are used to correlate these features. Finally, the feature selection attention-based mechanism is adopted to fuse the multi-layer features, and the multi-layer recurrent neural networks (RNNs) are utilized with bidirectional long short-term memory (Bi-LSTM) unit as the output layer. Furthermore, a novel logarithm exponential average error (LEAE) is proposed to overcome over-weighted problem. The multi-scale feature correlation network (MFCN) is evaluated on large-scale KITTI benchmarks (LKT), which is a subset of KITTI raw dataset, and NYU depth v2. The experiments indicate that the proposed unified network outperforms existing methods. This method also updates the state-of-the-art performance on LKT datasets. Importantly, the depth estimation method can be widely used for collision risk assessment and avoidance in driving assistance systems or automated pilot systems to achieve safety in a more economical and convenient way.

Community detection in dynamic social networks: A local evolutionary approach

2016 ◽  
Vol 43 (5) ◽  
pp. 615-634 ◽  
Author(s):  
Mohammad Ebrahim Samie ◽  
Ali Hamzeh
Keyword(s):  
Social Networks ◽  
Graph Mining ◽  
Local Information ◽  
Second Phase ◽  
Global Information ◽  
Two Phase ◽  
Dynamic Social Networks ◽  
Using Data ◽  
Global And Local ◽  
Mining Tools

Communities in social networks are groups of individuals who are connected with specific goals. Discovering information on the structure, members and types of changes of communities have always been of great interest. Despite the extensive global researches conducted on these, discovery has not been confirmed yet and researchers try to find methods and improve estimated techniques by using Data Mining tools, Graph Mining tools and artificial intelligence techniques. This paper proposes a novel two-phase approach based on global and local information to detect communities in social network. It explores the global information in the first phase and then exploits the local information in the second phase to discover communities more accurately. It also proposes a novel algorithm which exploits the local information and mines deeply for the second phase. Experimental results show that the proposed method has better performance and achieves more accurate results compared with the previous ones.

Do You Want to See the Tree? Ignore the Forest

2014 ◽  
Vol 61 (3) ◽  
pp. 205-214 ◽  
Author(s):  
Nicolas Poirel ◽  
Claire Sara Krakowski ◽  
Sabrina Sayah ◽  
Arlette Pineau ◽  
Olivier Houdé ◽  
...  
Keyword(s):  
Visual Recognition ◽  
Local Level ◽  
Local Information ◽  
Visual Environment ◽  
Global Information ◽  
Focus Attention ◽  
Global Level ◽  
Hierarchical Stimuli ◽  
Priming Paradigm ◽  
The One

The visual environment consists of global structures (e.g., a forest) made up of local parts (e.g., trees). When compound stimuli are presented (e.g., large global letters composed of arrangements of small local letters), the global unattended information slows responses to local targets. Using a negative priming paradigm, we investigated whether inhibition is required to process hierarchical stimuli when information at the local level is in conflict with the one at the global level. The results show that when local and global information is in conflict, global information must be inhibited to process local information, but that the reverse is not true. This finding has potential direct implications for brain models of visual recognition, by suggesting that when local information is conflicting with global information, inhibitory control reduces feedback activity from global information (e.g., inhibits the forest) which allows the visual system to process local information (e.g., to focus attention on a particular tree).

Intelligent recognition of semantic relationships based on antonymy

2020 ◽  
Vol 16 (3) ◽  
pp. 263-290
Author(s):  
Hui Guan ◽  
Chengzhen Jia ◽  
Hongji Yang
Keyword(s):  
Semantic Similarity ◽  
New Approach ◽  
Word Similarity ◽  
Semantic Relationships ◽  
Proposed Model ◽  
Path Distance ◽  
The Hierarchical Structure ◽  
Thinking Process ◽  
Similarity Measuring ◽  
Intelligent Recognition

Since computing semantic similarity tends to simulate the thinking process of humans, semantic dissimilarity must play a part in this process. In this paper, we present a new approach for semantic similarity measuring by taking consideration of dissimilarity into the process of computation. Specifically, the proposed measures explore the potential antonymy in the hierarchical structure of WordNet to represent the dissimilarity between concepts and then combine the dissimilarity with the results of existing methods to achieve semantic similarity results. The relation between parameters and the correlation value is discussed in detail. The proposed model is then applied to different text granularity levels to validate the correctness on similarity measurement. Experimental results show that the proposed approach not only achieves high correlation value against human ratings but also has effective improvement to existing path-distance based methods on the word similarity level, in the meanwhile effectively correct existing sentence similarity method in some cases in Microsoft Research Paraphrase Corpus and SemEval-2014 date set.

scholarly journals Neural Network Approach for Global Solar Irradiance Prediction at Extremely Short-Time-Intervals Using Particle Swarm Optimization Algorithm

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 1213
Author(s):  
Ahmed Aljanad ◽  
Nadia M. L. Tan ◽  
Vassilios G. Agelidis ◽  
Hussain Shareef
Keyword(s):  
Neural Networks ◽  
Particle Swarm Optimization ◽  
Solar Irradiance ◽  
Particle Swarm ◽  
Time Interval ◽  
Time Intervals ◽  
Swarm Optimization ◽  
Backpropagation Neural Networks ◽  
Proposed Model ◽  
Short Time

Hourly global solar irradiance (GSR) data are required for sizing, planning, and modeling of solar photovoltaic farms. However, operating and controlling such farms exposed to varying environmental conditions, such as fast passing clouds, necessitates GSR data to be available for very short time intervals. Classical backpropagation neural networks do not perform satisfactorily when predicting parameters within short intervals. This paper proposes a hybrid backpropagation neural networks based on particle swarm optimization. The particle swarm algorithm is used as an optimization algorithm within the backpropagation neural networks to optimize the number of hidden layers and neurons used and its learning rate. The proposed model can be used as a reliable model in predicting changes in the solar irradiance during short time interval in tropical regions such as Malaysia and other regions. Actual global solar irradiance data of 5-s and 1-min intervals, recorded by weather stations, are applied to train and test the proposed algorithm. Moreover, to ensure the adaptability and robustness of the proposed technique, two different cases are evaluated using 1-day and 3-days profiles, for two different time intervals of 1-min and 5-s each. A set of statistical error indices have been introduced to evaluate the performance of the proposed algorithm. From the results obtained, the 3-days profile’s performance evaluation of the BPNN-PSO are 1.7078 of RMSE, 0.7537 of MAE, 0.0292 of MSE, and 31.4348 of MAPE (%), at 5-s time interval, where the obtained results of 1-min interval are 0.6566 of RMSE, 0.2754 of MAE, 0.0043 of MSE, and 1.4732 of MAPE (%). The results revealed that proposed model outperformed the standalone backpropagation neural networks method in predicting global solar irradiance values for extremely short-time intervals. In addition to that, the proposed model exhibited high level of predictability compared to other existing models.

Chinese Image Captioning via Fuzzy Attention-based DenseNet-BiLSTM

2021 ◽  
Vol 17 (1s) ◽  
pp. 1-18 ◽  
Author(s):  
Huimin Lu ◽  
Rui Yang ◽  
Zhenrong Deng ◽  
Yonglin Zhang ◽  
Guangwei Gao ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Contextual Information ◽  
Image Features ◽  
Context Information ◽  
Global Information ◽  
Image Description ◽  
Image Captioning ◽  
Image Content ◽  
Single Feature ◽  
Proposed Model

Chinese image description generation tasks usually have some challenges, such as single-feature extraction, lack of global information, and lack of detailed description of the image content. To address these limitations, we propose a fuzzy attention-based DenseNet-BiLSTM Chinese image captioning method in this article. In the proposed method, we first improve the densely connected network to extract features of the image at different scales and to enhance the model’s ability to capture the weak features. At the same time, a bidirectional LSTM is used as the decoder to enhance the use of context information. The introduction of an improved fuzzy attention mechanism effectively improves the problem of correspondence between image features and contextual information. We conduct experiments on the AI Challenger dataset to evaluate the performance of the model. The results show that compared with other models, our proposed model achieves higher scores in objective quantitative evaluation indicators, including BLEU , BLEU , METEOR, ROUGEl, and CIDEr. The generated description sentence can accurately express the image content.

Sign in / Sign up

Export Citation Format

Share Document