scholarly journals Unsupervised Hashing with Contrastive Information Bottleneck

2021 ◽  
Author(s):  
Zexuan Qiu ◽  
Qinliang Su ◽  
Zijing Ou ◽  
Jianxing Yu ◽  
Changyou Chen
Keyword(s):  
Input Data ◽  
Semantic Information ◽  
Original Data ◽  
Background Information ◽  
Binary Representation ◽  
Strong Connection ◽  
Recent Success ◽  
Information Bottleneck ◽  
Proposed Model ◽  
Continuous Representations

Many unsupervised hashing methods are implicitly established on the idea of reconstructing the input data, which basically encourages the hashing codes to retain as much information of original data as possible. However, this requirement may force the models spending lots of their effort on reconstructing the unuseful background information, while ignoring to preserve the discriminative semantic information that is more important for the hashing task. To tackle this problem, inspired by the recent success of contrastive learning in learning continuous representations, we propose to adapt this framework to learn binary hashing codes. Specifically, we first propose to modify the objective function to meet the specific requirement of hashing and then introduce a probabilistic binary representation layer into the model to facilitate end-to-end training of the entire model. We further prove the strong connection between the proposed contrastive-learning-based hashing method and the mutual information, and show that the proposed model can be considered under the broader framework of the information bottleneck (IB). Under this perspective, a more general hashing model is naturally obtained. Extensive experimental results on three benchmark image datasets demonstrate that the proposed hashing method significantly outperforms existing baselines.

scholarly journals Neuro-Fuzzy Transformation with Minimize Entropy Principle to Create New Features for Particulate Matter Prediction

2021 ◽  
Vol 11 (14) ◽  
pp. 6590
Author(s):  
Krittakom Srijiranon ◽  
Narissara Eiamkanitchat
Keyword(s):  
Particulate Matter ◽  
Fuzzy Model ◽  
Original Data ◽  
Northern Region ◽  
National Standard ◽  
Minimum Entropy ◽  
Fuzzy Transformation ◽  
Neuro Fuzzy ◽  
Proposed Model ◽  
Entropy Principle

Air pollution is a major global issue. In Thailand, this issue continues to increase every year, similar to other countries, especially during the dry season in the northern region. In this period, particulate matter with aerodynamic diameters smaller than 10 and 2.5 micrometers, known as PM10 and PM2.5, are important pollutants, most of which exceed the national standard levels, the so-called Thailand air quality index (T-AQI). Therefore, this study created a prediction model to classify T-AQI calculated from both types of PM. The neuro-fuzzy model with a minimum entropy principle model is proposed to transform the original data into new informative features. The processes in this model are able to discover appropriate separation points of the trapezoidal membership function by applying the minimum entropy principle. The membership value of the fuzzy section is then passed to the neural section to create a new data feature, the PM level, for each hour of the day. Finally, as an analytical process to obtain new knowledge, predictive models are created using new data features for better classification results. Various experiments were utilized to find an appropriate structure with high prediction accuracy. The results of the proposed model were favorable for predicting both types of PM up to three hours in advance. The proposed model can help people who are planning short-term outdoor activities.

scholarly journals Dual Protectıon for Data usıng Steganographıc Technıques with Embedded Framework

2019 ◽  
Vol 8 (5S3) ◽  
pp. 155-159
Keyword(s):  
High Performance ◽  
Data Communication ◽  
Original Data ◽  
Cover Image ◽  
Original Text ◽  
Dual Protection ◽  
Proposed Model ◽  
Encryption And Decryption ◽  
Secured Data

As the world is getting digitalized, the rush for need of secured data communication is overtop. Provoked by the vulnerability of human visual system to understand the progressive changes in the scenes, a new steganography method is proposed. The paper represents a double protection methodology for secured transmission of data. The original data is hidden inside a cover image using LSB substitution algorithm. The image obtained is inserted inside a frame of the video producing a stego-video. Stego-video attained is less vulnerable to attacks. After decryption phase, the original text is obtained which is error-free and the output image obtained is similar as the cover image. The quality of stego-video is high and there is no need for additional bandwidth for transmission. The hardware implement is required in order to calculate the corresponding analytical results. The proposed algorithm is examined and realized for various encryption standards using Raspberry Pi3 embedded hardware. The results obtained focuses on the attributes of the proposed model. On comparing with other conventional algorithms, the proposed scheme exhibits high performance in both encryption and decryption process with increase in efficiency of secured data communication.

scholarly journals Specializing Word Embeddings (for Parsing) by Information Bottleneck (Extended Abstract)

2020 ◽  
Author(s):  
Xiang Lisa Li ◽  
Jason Eisner
Keyword(s):  
Dimensionality Reduction ◽  
Semantic Information ◽  
State Of The Art ◽  
Word Embedding ◽  
Discrete Version ◽  
Word Embeddings ◽  
Continuous Version ◽  
Continuous Vector ◽  
Information Bottleneck ◽  
Art Performance

Pre-trained word embeddings like ELMo and BERT contain rich syntactic and semantic information, resulting in state-of-the-art performance on various tasks. We propose a very fast variational information bottleneck (VIB) method to nonlinearly compress these embeddings, keeping only the information that helps a discriminative parser. We compress each word embedding to either a discrete tag or a continuous vector. In the discrete version, our automatically compressed tags form an alternative tag set: we show experimentally that our tags capture most of the information in traditional POS tag annotations, but our tag sequences can be parsed more accurately at the same level of tag granularity. In the continuous version, we show experimentally that moderately compressing the word embeddings by our method yields a more accurate parser in 8 of 9 languages, unlike simple dimensionality reduction.

What makes users willing or hesitant to use Fintech?: the moderating effect of user type

2018 ◽  
Vol 118 (3) ◽  
pp. 541-569 ◽  
Author(s):  
Hyun-Sun Ryu
Keyword(s):  
Least Squares Method ◽  
Original Data ◽  
The Novel ◽  
Continuance Intention ◽  
Content Type ◽  
Factors Affecting ◽  
Proposed Model ◽  
Negative Effect ◽  
Partial Least Squares Method ◽  
Benefit And Risk

Purpose The purpose of this paper is to better understand why people are willing or hesitant to use Financial technology (Fintech) as well as to determine whether the effect of perceived benefits and risks of continuance intention differs depending on user types. Design/methodology/approach Original data were collected via a survey of 243 participants with Fintech usage experience. The partial least squares method was used to test the proposed model. Findings The results reveal that legal risk had the most negative effect on the Fintech continuance intention, while convenience had the strongest positive effect. Differences in specific benefit and risk impacts are found between early and late adopters. Originality/value This empirical study contributes to the novel understanding of the benefit and risk factors affecting the Fintech continuance intention.

scholarly journals The Effect of Evidence Transfer on Latent Feature Relevance for Clustering

Informatics ◽  
2019 ◽  
Vol 6 (2) ◽  
pp. 17
Author(s):  
Athanasios Davvetas ◽  
Iraklis A. Klampanos ◽  
Spiros Skiadopoulos ◽  
Vangelis Karkaletsis
Keyword(s):  
Mutual Information ◽  
Ground Truth ◽  
Original Data ◽  
Information Theoretic ◽  
Information Bottleneck ◽  
Latent Space ◽  
Before And After ◽  
Feature Relevance ◽  
Latent Representations ◽  
Transfer Method

Evidence transfer for clustering is a deep learning method that manipulates the latent representations of an autoencoder according to external categorical evidence with the effect of improving a clustering outcome. Evidence transfer’s application on clustering is designed to be robust when introduced with a low quality of evidence, while increasing the effectiveness of the clustering accuracy during relevant corresponding evidence. We interpret the effects of evidence transfer on the latent representation of an autoencoder by comparing our method to the information bottleneck method. Information bottleneck is an optimisation problem of finding the best tradeoff between maximising the mutual information of data representations and a task outcome while at the same time being effective in compressing the original data source. We posit that the evidence transfer method has essentially the same objective regarding the latent representations produced by an autoencoder. We verify our hypothesis using information theoretic metrics from feature selection in order to perform an empirical analysis over the information that is carried through the bottleneck of the latent space. We use the relevance metric to compare the overall mutual information between the latent representations and the ground truth labels before and after their incremental manipulation, as well as, to study the effects of evidence transfer regarding the significance of each latent feature.

scholarly journals Appearance and Motion Enhancement for Video-Based Person Re-Identification

2020 ◽  
Vol 34 (07) ◽  
pp. 11394-11401
Author(s):  
Shuzhao Li ◽  
Huimin Yu ◽  
Haoji Hu
Keyword(s):  
Semantic Information ◽  
State Of The Art ◽  
Complex Model ◽  
The State ◽  
Final Model ◽  
Backbone Network ◽  
Proposed Model ◽  
Art Performance ◽  
Attribute Recognition

In this paper, we propose an Appearance and Motion Enhancement Model (AMEM) for video-based person re-identification to enrich the two kinds of information contained in the backbone network in a more interpretable way. Concretely, human attribute recognition under the supervision of pseudo labels is exploited in an Appearance Enhancement Module (AEM) to help enrich the appearance and semantic information. A Motion Enhancement Module (MEM) is designed to capture the identity-discriminative walking patterns through predicting future frames. Despite a complex model with several auxiliary modules during training, only the backbone model plus two small branches are kept for similarity evaluation which constitute a simple but effective final model. Extensive experiments conducted on three popular video-based person ReID benchmarks demonstrate the effectiveness of our proposed model and the state-of-the-art performance compared with existing methods.

Modelling the relationship between population density and air quality using fractional Hausdorff grey multivariate model

Kybernetes ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Kaihe Shi ◽  
Lifeng Wu
Keyword(s):  
Air Quality ◽  
Population Density ◽  
Composite Index ◽  
Original Data ◽  
Multivariate Model ◽  
Grey Model ◽  
Content Type ◽  
New Information ◽  
Proposed Model ◽  
Comparison Results

Purpose The proposed model can emphasize the priority of new information and can extract messages from the first pair of original data. The comparison results show that the proposed model can improve the traditional grey model. Design/methodology/approach The grey multivariate model with fractional Hausdorff derivative is firstly put forward to enhance the forecasting accuracy of traditional grey model. Findings The proposed model is used to predict the air quality composite index (AQCI) in ten cities respectively. Originality/value The effect of population density on AQCI in cities with poor air quality is not as significant as that of the cities with better air quality.

scholarly journals A Novel Grey Power-markov Model for the Prediction of China's Electricity Consumption

2021 ◽  
Author(s):  
Liqin Sun ◽  
Youlong Yang ◽  
Tong Ning ◽  
Jiadi Zhu
Keyword(s):  
Prediction Models ◽  
Demand Forecasting ◽  
Electricity Consumption ◽  
Original Data ◽  
Development Trend ◽  
Statistical Hypothesis ◽  
Grey Prediction ◽  
New Information ◽  
Proposed Model ◽  
Grey Models

Abstract The grey prediction models of time series are widely used in demand forecasting because only limited data can be used to build the models and no statistical hypothesis is needed. In this paper, a grey power Markov prediction model (RGPMM(λ,1,1)) with time-varying parameters is proposed. This model is based on the principle of “new information priority”, combined with rolling mechanism and Markov theory, and the prediction residual error is modified to further improve the prediction accuracy. Compared with the classic grey models, the new model not only overcomes the inherent defect of poor adaptability to the original data, but also uses real-time information to better reflect the nonlinear characteristics of the original data, so it can be used to describe and predict the nonlinear development trend of things. In order to verify the validity and applicability of the model, the proposed model is used to forecast the total electric consumption in China. The experimental results show that the proposed model has a better prediction effect than other grey models. The proposed model is used to forecast China’s total electricity consumption in the next six years from 2018 to 2023.

scholarly journals Commonsense Knowledge Aware Conversation Generation with Graph Attention

2018 ◽  
Author(s):  
Hao Zhou ◽  
Tom Young ◽  
Minlie Huang ◽  
Haizhou Zhao ◽  
Jingfang Xu ◽  
...  
Keyword(s):  
Language Processing ◽  
Large Scale ◽  
Semantic Information ◽  
Attention Mechanism ◽  
Generation Model ◽  
Dynamic Graph ◽  
Commonsense Knowledge ◽  
Word Generation ◽  
Proposed Model ◽  
Knowledge Graphs

Commonsense knowledge is vital to many natural language processing tasks. In this paper, we present a novel open-domain conversation generation model to demonstrate how large-scale commonsense knowledge can facilitate language understanding and generation. Given a user post, the model retrieves relevant knowledge graphs from a knowledge base and then encodes the graphs with a static graph attention mechanism, which augments the semantic information of the post and thus supports better understanding of the post. Then, during word generation, the model attentively reads the retrieved knowledge graphs and the knowledge triples within each graph to facilitate better generation through a dynamic graph attention mechanism. This is the first attempt that uses large-scale commonsense knowledge in conversation generation. Furthermore, unlike existing models that use knowledge triples (entities) separately and independently, our model treats each knowledge graph as a whole, which encodes more structured, connected semantic information in the graphs. Experiments show that the proposed model can generate more appropriate and informative responses than state-of-the-art baselines. 

scholarly journals THE EFFECT OF AFFECTIVE ORGANIZATIONAL COMMITMENT TOWARDS INNOVATION CAPABILITY AND ITS IMPACT TO JOB PERFORMANCE IN FAMILY BUSINESS

2020 ◽  
Vol 9 (2) ◽  
pp. 99-110
Author(s):  
Yohana Cahya Wibowo ◽  
Natalia Christiani
Keyword(s):  
Organizational Commitment ◽  
Job Performance ◽  
Family Business ◽  
Original Data ◽  
Business Community ◽  
Innovation Capability ◽  
Affective Organizational Commitment ◽  
Online Questionnaire ◽  
Proposed Model

The purpose of this research is to find out about the effect of affective organizational commitment towards innovation capability and its impact to job performance in family business. Methodology – the original data was taken through an online questionnaire with 100 respondents who are members of Family Business Community in Universitas Ciputra along with the non-members. The SmartPLS 3.0 Statistics Program was used to test the proposed model. Findings– Result shows that affective organizational commitment significantly affects innovation capability and job performance and innovation capability significantly affects job performance.

Sign in / Sign up

Export Citation Format

Share Document