Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280573
Shin-Ying Huang, Fang Yu, R. Tsaih, Yennun Huang
Detecting anomaly behavior in large network traffic data has presented a great challenge in designing effective intrusion detection systems. We propose an adaptive model to learn majority patterns under a dynamic changing environment. We first propose unsupervised learning on data abstraction to extract essential features of samples. We then adopt incremental majority learning with iterative evolutions on fitting envelopes to characterize the majority of samples within moving windows. A network traffic sample is considered an anomaly if its abstract feature falls on the outside of the fitting envelope. We justify the effectiveness of the presented approach against 150000+ traffic samples from the NSL-KDD dataset in training and testing, demonstrating positive promise in detecting network attacks by identifying samples that have abnormal features.
{"title":"Network-traffic anomaly detection with incremental majority learning","authors":"Shin-Ying Huang, Fang Yu, R. Tsaih, Yennun Huang","doi":"10.1109/IJCNN.2015.7280573","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280573","url":null,"abstract":"Detecting anomaly behavior in large network traffic data has presented a great challenge in designing effective intrusion detection systems. We propose an adaptive model to learn majority patterns under a dynamic changing environment. We first propose unsupervised learning on data abstraction to extract essential features of samples. We then adopt incremental majority learning with iterative evolutions on fitting envelopes to characterize the majority of samples within moving windows. A network traffic sample is considered an anomaly if its abstract feature falls on the outside of the fitting envelope. We justify the effectiveness of the presented approach against 150000+ traffic samples from the NSL-KDD dataset in training and testing, demonstrating positive promise in detecting network attacks by identifying samples that have abnormal features.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"26 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78690758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280530
Lu Lu, Haijun Zhang
This paper introduces a new framework for author recommending using Multi-Layer Self-Organizing Map (ML-SOM). Concretely, an author is modeled by a tree-structured representation, and an MLSOM-based system is used as an efficient solution to the content-based author recommending problem. The tree-structured representation formulates author features in a hierarchy of author biography, written books and book comments. To efficiently tackle the tree-structured representation, we use an MLSOM algorithm that serves as a clustering technique to handle authors. The effectiveness of our approach was examined in a large-scale dataset containing 7426 authors, 205805 books they wrote, and 3027502 comments that readers have provided. The experimental results corroborate that the proposed approach outperforms current algorithms and can provide a promising solution to author recommendation.
{"title":"A tree-structured representation for book author and its recommendation using multilayer SOM","authors":"Lu Lu, Haijun Zhang","doi":"10.1109/IJCNN.2015.7280530","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280530","url":null,"abstract":"This paper introduces a new framework for author recommending using Multi-Layer Self-Organizing Map (ML-SOM). Concretely, an author is modeled by a tree-structured representation, and an MLSOM-based system is used as an efficient solution to the content-based author recommending problem. The tree-structured representation formulates author features in a hierarchy of author biography, written books and book comments. To efficiently tackle the tree-structured representation, we use an MLSOM algorithm that serves as a clustering technique to handle authors. The effectiveness of our approach was examined in a large-scale dataset containing 7426 authors, 205805 books they wrote, and 3027502 comments that readers have provided. The experimental results corroborate that the proposed approach outperforms current algorithms and can provide a promising solution to author recommendation.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"53 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72682105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280473
Marco Fagiani, S. Squartini, M. Severini, F. Piazza
In this paper, a novelty detection algorithm for the identification of leakages in smart water/gas grid contexts is proposed. It is based on two separate stages: the first deals with the creation of the statistical leakage-free model, whereas the second evaluates the eventual occurrence of leakage on the basis of the model likelihood. Up to the authors' knowledge, this approach has never been used in the application scenario of interest. A set of several features are extracted from the Almanac of Minutely Power Dataset, and a suboptimal selection is executed to determinate the best combination. The abnormal event (leakage) is induced by manipulating the consumption in the test set. A total of 10 background models are created, by employing both Gaussian Mixture Models (GMMs) and Hidden Markov Models (HMMs) under a comparative perspective, and each of them is adopted to detect 10 leakages, with random duration, length and starting time. Finally, the performance are evaluated in terms of Area Under Curve (AUC) of the Receiver Operating Characteristic (ROC). Obtained results are more than encouraging: the best average AUCs of 85.60% and 87.97% are achieved with HMM, at 1 minute resolution, for natural gas and water, respectively. Specifically, considering true detection rates (TDRs) of 100%, the natural gas exhibits an overall false detection rate (FDR) of 17.11%, and the water achieves an overall FDR of 13.79%.
{"title":"A novelty detection approach to identify the occurrence of leakage in smart gas and water grids","authors":"Marco Fagiani, S. Squartini, M. Severini, F. Piazza","doi":"10.1109/IJCNN.2015.7280473","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280473","url":null,"abstract":"In this paper, a novelty detection algorithm for the identification of leakages in smart water/gas grid contexts is proposed. It is based on two separate stages: the first deals with the creation of the statistical leakage-free model, whereas the second evaluates the eventual occurrence of leakage on the basis of the model likelihood. Up to the authors' knowledge, this approach has never been used in the application scenario of interest. A set of several features are extracted from the Almanac of Minutely Power Dataset, and a suboptimal selection is executed to determinate the best combination. The abnormal event (leakage) is induced by manipulating the consumption in the test set. A total of 10 background models are created, by employing both Gaussian Mixture Models (GMMs) and Hidden Markov Models (HMMs) under a comparative perspective, and each of them is adopted to detect 10 leakages, with random duration, length and starting time. Finally, the performance are evaluated in terms of Area Under Curve (AUC) of the Receiver Operating Characteristic (ROC). Obtained results are more than encouraging: the best average AUCs of 85.60% and 87.97% are achieved with HMM, at 1 minute resolution, for natural gas and water, respectively. Specifically, considering true detection rates (TDRs) of 100%, the natural gas exhibits an overall false detection rate (FDR) of 17.11%, and the water achieves an overall FDR of 13.79%.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"42 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79755684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280410
Xiaoyao Yin, Lu Han, Hui Bai, Xiaochen Bo, Yun Bai, Cong Niu, Naiyang Guan, Zhigang Luo
Modern understanding of microbiology largely lays foundation in the biological characterization of microorganisms. However, the landscape relationships of host transcriptional response (HTR) to different bacterial pathogens have not yet been systematically explored. Here, we established the first generation of HTR network (HTRN) according to the HTR similarities among 21 different human pathogenic bacterial species by integrating 258 pairs of host cellular gene expression profiles upon infections. Further, the network was dissected into five bacterial communities of more consensus internal HTR. Interestingly, analysis of signature genes across different communities revealed that distinct community signatures (CS) present differential gene expression patterns. Functional annotation suggested a common feature of host cell response to bacterial infections that specific functional gene clusters (BPs and/or signaling pathways) were preferentially elicited or subverted by community bacterial pathogens. Notably, community signatures (especially key associators participating dissimilar functional profiles) were highly enriched of GWAS disease-related genes, which associated bacterial infections with common and specific non-infectious human disease(s). About 40% of the associations were confirmed by literature investigation that further indicated possible/potential association directionality. Our characterization and analysis were the first to feature differential community HTRs upon bacterial pathogen infections and suggested new perspective of understanding infection-disease associations and underlying pathogenesis.
{"title":"New insights into the landscape relationships of host response to bacterial pathogens","authors":"Xiaoyao Yin, Lu Han, Hui Bai, Xiaochen Bo, Yun Bai, Cong Niu, Naiyang Guan, Zhigang Luo","doi":"10.1109/IJCNN.2015.7280410","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280410","url":null,"abstract":"Modern understanding of microbiology largely lays foundation in the biological characterization of microorganisms. However, the landscape relationships of host transcriptional response (HTR) to different bacterial pathogens have not yet been systematically explored. Here, we established the first generation of HTR network (HTRN) according to the HTR similarities among 21 different human pathogenic bacterial species by integrating 258 pairs of host cellular gene expression profiles upon infections. Further, the network was dissected into five bacterial communities of more consensus internal HTR. Interestingly, analysis of signature genes across different communities revealed that distinct community signatures (CS) present differential gene expression patterns. Functional annotation suggested a common feature of host cell response to bacterial infections that specific functional gene clusters (BPs and/or signaling pathways) were preferentially elicited or subverted by community bacterial pathogens. Notably, community signatures (especially key associators participating dissimilar functional profiles) were highly enriched of GWAS disease-related genes, which associated bacterial infections with common and specific non-infectious human disease(s). About 40% of the associations were confirmed by literature investigation that further indicated possible/potential association directionality. Our characterization and analysis were the first to feature differential community HTRs upon bacterial pathogen infections and suggested new perspective of understanding infection-disease associations and underlying pathogenesis.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"103 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80298299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280753
S. Otte, A. Zell, M. Liwicki
The recently introduced Dynamic Cortex Memory (DCM) is an extension of the Long Short Term Memory (LSTM) providing a systematic inter-gate connection infrastructure. In this paper the behavior of DCM networks is studied in more detail and their potential in the field of gradient-based sequence learning is investigated. Hereby, DCM networks are analyzed regarding particular key features of neural signal processing systems, namely, their robustness to noise and their ability of time warping. Throughout all experiments we show that DCMs converge faster and yield better results than LSTMs. Hereby, DCM networks require overall less weights than pure LSTM networks to achieve the same or even better results. Besides, a promising neurally implemented just-in-time online signal filter approach is presented, which is latency-free and still provides an accurate filtering performance much better than conventional low-pass filters. We also show that the neural networks can do explicit time warping even better than the Dynamic Time Warping (DTW) algorithm, which is a specialized method developed for this task.
{"title":"An analysis of Dynamic Cortex Memory networks","authors":"S. Otte, A. Zell, M. Liwicki","doi":"10.1109/IJCNN.2015.7280753","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280753","url":null,"abstract":"The recently introduced Dynamic Cortex Memory (DCM) is an extension of the Long Short Term Memory (LSTM) providing a systematic inter-gate connection infrastructure. In this paper the behavior of DCM networks is studied in more detail and their potential in the field of gradient-based sequence learning is investigated. Hereby, DCM networks are analyzed regarding particular key features of neural signal processing systems, namely, their robustness to noise and their ability of time warping. Throughout all experiments we show that DCMs converge faster and yield better results than LSTMs. Hereby, DCM networks require overall less weights than pure LSTM networks to achieve the same or even better results. Besides, a promising neurally implemented just-in-time online signal filter approach is presented, which is latency-free and still provides an accurate filtering performance much better than conventional low-pass filters. We also show that the neural networks can do explicit time warping even better than the Dynamic Time Warping (DTW) algorithm, which is a specialized method developed for this task.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"2 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79006537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280318
G. Cirrincione, J. Hérault, V. Randazzo
Real time pattern recognition applications often deal with high dimensional data, which require a data reduction step which is only performed offline. However, this loses the possibility of adaption to a changing environment. This is also true for other applications different from pattern recognition, like data visualization for input inspection. Only linear projections, like the principal component analysis, can work in real time by using iterative algorithms while all known nonlinear techniques cannot be implemented in such a way and actually always work on the whole database at each epoch. Among these nonlinear tools, the Curvilinear Component Analysis (CCA), which is a non-convex technique based on the preservation of the local distances into the lower dimensional space, plays an important role. This paper presents the online version of CCA. It inherits the same features of CCA, is adaptive in real time and tracks non-stationary high dimensional distributions. It is composed of neurons with two weights: one, pointing to the input space, quantizes the data distribution, and the other, pointing to the output space, represents the projection of the first weight. This on-line CCA has been conceived not only for the previously cited applications, but also as a basic tool for more complex supervised neural networks for modelling very complex high dimensional data. This algorithm is tested on 2-D and 3-D synthetic data and on an experimental database concerning the bearing faults of an electrical motor, with the goal of novelty (fault) detection.
{"title":"The on-line curvilinear component analysis (onCCA) for real-time data reduction","authors":"G. Cirrincione, J. Hérault, V. Randazzo","doi":"10.1109/IJCNN.2015.7280318","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280318","url":null,"abstract":"Real time pattern recognition applications often deal with high dimensional data, which require a data reduction step which is only performed offline. However, this loses the possibility of adaption to a changing environment. This is also true for other applications different from pattern recognition, like data visualization for input inspection. Only linear projections, like the principal component analysis, can work in real time by using iterative algorithms while all known nonlinear techniques cannot be implemented in such a way and actually always work on the whole database at each epoch. Among these nonlinear tools, the Curvilinear Component Analysis (CCA), which is a non-convex technique based on the preservation of the local distances into the lower dimensional space, plays an important role. This paper presents the online version of CCA. It inherits the same features of CCA, is adaptive in real time and tracks non-stationary high dimensional distributions. It is composed of neurons with two weights: one, pointing to the input space, quantizes the data distribution, and the other, pointing to the output space, represents the projection of the first weight. This on-line CCA has been conceived not only for the previously cited applications, but also as a basic tool for more complex supervised neural networks for modelling very complex high dimensional data. This algorithm is tested on 2-D and 3-D synthetic data and on an experimental database concerning the bearing faults of an electrical motor, with the goal of novelty (fault) detection.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"34 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81638000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280469
C. Cervellera, Mauro Gaggero, Danilo Macciò, R. Marcialis
This work addresses the problem of learning an unknown function from data when local models are employed. In particular, kernel smoothing models are considered, which use kernels in a straightforward fashion by modeling the output as a weighted average of values observed in a neighborhood of the input. Such models are a popular alternative to other kernel paradigms, such as support vector machines (SVM), due to their very light computational burden. The purpose of this work is to prove that a smart deterministic selection of the observation points can be advantageous with respect to input data coming from a pure random sampling. Apart from the theoretical interest, this has a practical implication in all the cases in which one can control the generation of the input samples (e.g., in applications from robotics, dynamic programming, optimization, mechanics, etc.) To this purpose, lattice point sets (LPSs), a special kind of sampling schemes commonly employed for efficient numerical integration, are investigated. It is proved that building local kernel smoothers using LPSs guarantees universal approximation property with better rates with respect to i.i.d. sampling. Then, a rule for automatic kernel width selection, making the computational burden of building the model negligible, is introduced to show how the regular structure of the lattice can lead to practical advantages. Simulation results are also provided to test in practice the performance of the proposed methods.
{"title":"Lattice point sets for efficient kernel smoothing models","authors":"C. Cervellera, Mauro Gaggero, Danilo Macciò, R. Marcialis","doi":"10.1109/IJCNN.2015.7280469","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280469","url":null,"abstract":"This work addresses the problem of learning an unknown function from data when local models are employed. In particular, kernel smoothing models are considered, which use kernels in a straightforward fashion by modeling the output as a weighted average of values observed in a neighborhood of the input. Such models are a popular alternative to other kernel paradigms, such as support vector machines (SVM), due to their very light computational burden. The purpose of this work is to prove that a smart deterministic selection of the observation points can be advantageous with respect to input data coming from a pure random sampling. Apart from the theoretical interest, this has a practical implication in all the cases in which one can control the generation of the input samples (e.g., in applications from robotics, dynamic programming, optimization, mechanics, etc.) To this purpose, lattice point sets (LPSs), a special kind of sampling schemes commonly employed for efficient numerical integration, are investigated. It is proved that building local kernel smoothers using LPSs guarantees universal approximation property with better rates with respect to i.i.d. sampling. Then, a rule for automatic kernel width selection, making the computational burden of building the model negligible, is introduced to show how the regular structure of the lattice can lead to practical advantages. Simulation results are also provided to test in practice the performance of the proposed methods.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"30 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84436673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280829
G. Tanaka, T. Yamane, D. Nakano, R. Nakane, Y. Katayama
This study explores efficient structures of artificial neural networks for associative memories. Motivated by the real brain structure and the demand of energy efficiency in hardware implementation, we consider neural networks with sparse modular structures. Numerical experiments are performed to clarify how the storage capacity of associative memory depends on regularity and randomness of the network structures. We first show that a fully regularized network, suited for design of hardware, has poor recall performance and a fully random network, undesired for hardware implementation, yields excellent recall performance. For seeking a network structure with good performance and high implementability, we consider four different modular networks constructed based on different combinations of regularity and randomness. From the results of associative memory tests for these networks, we find that the combination of random intramodule connections and regular intermodule connections works better than the other cases. Our results suggest that the parallel usage of regularity and randomness in network structures could be beneficial for developing energy-efficient neural networks.
{"title":"Regularity and randomness in modular network structures for neural associative memories","authors":"G. Tanaka, T. Yamane, D. Nakano, R. Nakane, Y. Katayama","doi":"10.1109/IJCNN.2015.7280829","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280829","url":null,"abstract":"This study explores efficient structures of artificial neural networks for associative memories. Motivated by the real brain structure and the demand of energy efficiency in hardware implementation, we consider neural networks with sparse modular structures. Numerical experiments are performed to clarify how the storage capacity of associative memory depends on regularity and randomness of the network structures. We first show that a fully regularized network, suited for design of hardware, has poor recall performance and a fully random network, undesired for hardware implementation, yields excellent recall performance. For seeking a network structure with good performance and high implementability, we consider four different modular networks constructed based on different combinations of regularity and randomness. From the results of associative memory tests for these networks, we find that the combination of random intramodule connections and regular intermodule connections works better than the other cases. Our results suggest that the parallel usage of regularity and randomness in network structures could be beneficial for developing energy-efficient neural networks.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"89 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84475956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280513
Di Yao, Jingping Bi, Jianhui Huang, Jin Zhu
With the development of internet, there are billions of short texts generated each day. However, the accuracy of large scale short text classification is poor due to the data sparseness. Traditional methods used to use external dataset to enrich the representation of document and solve the data sparsity problem. But external dataset which matches the specific short texts is hard to find. In this paper, we propose a framework to solve the data sparsity problem without using external dataset. Our framework deal with large scale short text by making the most of semantic similarity of words which learned from the training short texts. First, we learn word distributed representation and measure the word semantic similarity from the training short texts. Then, we propose a method which enrich the document representation by using the word semantic similarity information. At last, we build classifiers based on the enriched representation. We evaluate our framework on both the benchmark dataset(Standford Sentiment Treebank) and the large scale Chinese news title dataset which collected by ourselves. For the benchmark dataset, using our framework can improve 3% classification accuracy. The result we tested on the large scale Chinese news title dataset shows that our framework achieve better result with the increase of the training set size.
{"title":"A word distributed representation based framework for large-scale short text classification","authors":"Di Yao, Jingping Bi, Jianhui Huang, Jin Zhu","doi":"10.1109/IJCNN.2015.7280513","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280513","url":null,"abstract":"With the development of internet, there are billions of short texts generated each day. However, the accuracy of large scale short text classification is poor due to the data sparseness. Traditional methods used to use external dataset to enrich the representation of document and solve the data sparsity problem. But external dataset which matches the specific short texts is hard to find. In this paper, we propose a framework to solve the data sparsity problem without using external dataset. Our framework deal with large scale short text by making the most of semantic similarity of words which learned from the training short texts. First, we learn word distributed representation and measure the word semantic similarity from the training short texts. Then, we propose a method which enrich the document representation by using the word semantic similarity information. At last, we build classifiers based on the enriched representation. We evaluate our framework on both the benchmark dataset(Standford Sentiment Treebank) and the large scale Chinese news title dataset which collected by ourselves. For the benchmark dataset, using our framework can improve 3% classification accuracy. The result we tested on the large scale Chinese news title dataset shows that our framework achieve better result with the increase of the training set size.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"28 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84870870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280745
A. Siemon, S. Menzel, R. Waser, E. Linn
Redox-based resistive switching devices are an emerging class of non-volatile ultra-scalable memory and logic devices. These devices offer complex internal device physics leading to rich dynamical behavior. Memristive device models are intended to reproduce the underlying redox-based resistive switching device behavior accurately to enable proper circuit simulations. A specific feature of resistively switching devices is the controllability of multi-level resistive states by using a current compliance during the SET operation. Here, we consider a one-transistor-one-resistive-switch circuit to study the multi-level capability of three different types of memristive models. The feasibility of current compliance induced multi-level resistance state control is a check for the accuracy of the memristive device model.
{"title":"Controllability of multi-level states in memristive device models using a transistor as current compliance during SET operation","authors":"A. Siemon, S. Menzel, R. Waser, E. Linn","doi":"10.1109/IJCNN.2015.7280745","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280745","url":null,"abstract":"Redox-based resistive switching devices are an emerging class of non-volatile ultra-scalable memory and logic devices. These devices offer complex internal device physics leading to rich dynamical behavior. Memristive device models are intended to reproduce the underlying redox-based resistive switching device behavior accurately to enable proper circuit simulations. A specific feature of resistively switching devices is the controllability of multi-level resistive states by using a current compliance during the SET operation. Here, we consider a one-transistor-one-resistive-switch circuit to study the multi-level capability of three different types of memristive models. The feasibility of current compliance induced multi-level resistance state control is a check for the accuracy of the memristive device model.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"5 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85374200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：