Pub Date : 2011-10-03DOI: 10.1109/IJCNN.2011.6033439
D. Querlioz, O. Bichler, C. Gamrat
We propose a design methodology to exploit adaptive nanodevices (memristors), virtually immune to their variability. Memristors are used as synapses in a spiking neural network performing unsupervised learning. The memristors learn through an adaptation of spike timing dependent plasticity. Neurons' threshold is adjusted following a homeostasis-type rule. System level simulations on a textbook case show that performance can compare with traditional supervised networks of similar complexity. They also show the system can retain functionality with extreme variations of various memristors' parameters, thanks to the robustness of the scheme, its unsupervised nature, and the power of homeostasis. Additionally the network can adjust to stimuli presented with different coding schemes.
{"title":"Simulation of a memristor-based spiking neural network immune to device variations","authors":"D. Querlioz, O. Bichler, C. Gamrat","doi":"10.1109/IJCNN.2011.6033439","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033439","url":null,"abstract":"We propose a design methodology to exploit adaptive nanodevices (memristors), virtually immune to their variability. Memristors are used as synapses in a spiking neural network performing unsupervised learning. The memristors learn through an adaptation of spike timing dependent plasticity. Neurons' threshold is adjusted following a homeostasis-type rule. System level simulations on a textbook case show that performance can compare with traditional supervised networks of similar complexity. They also show the system can retain functionality with extreme variations of various memristors' parameters, thanks to the robustness of the scheme, its unsupervised nature, and the power of homeostasis. Additionally the network can adjust to stimuli presented with different coding schemes.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133215833","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033654
P. Werbos
There has been important new cross-disciplinary work using neural network mathematics to unify key issues in engineering, technology, psychology and neuroscience - and many opportunities to create a discrete revolution in science by pushing this work further. This strain of research has a natural link to clinical and subjective human experience - the “first person science” of the mind. This paper discusses why and how, and gives several examples of links between neural network models and key phenomena in human experience, such as Freud's “psychic energy,” the role of traumatic experience, the interpretation of dreams and creativity and the cultivation of human potential and sanity in general, and the biological foundations of language.
{"title":"Neural networks as a path to self-awareness","authors":"P. Werbos","doi":"10.1109/IJCNN.2011.6033654","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033654","url":null,"abstract":"There has been important new cross-disciplinary work using neural network mathematics to unify key issues in engineering, technology, psychology and neuroscience - and many opportunities to create a discrete revolution in science by pushing this work further. This strain of research has a natural link to clinical and subjective human experience - the “first person science” of the mind. This paper discusses why and how, and gives several examples of links between neural network models and key phenomena in human experience, such as Freud's “psychic energy,” the role of traumatic experience, the interpretation of dreams and creativity and the cultivation of human potential and sanity in general, and the biological foundations of language.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127871909","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033269
Isabel Volpe, V. Moreira, C. Huyck
One of the main tasks in Information Retrieval is to match a user query to the documents that are relevant for it. This matching is challenging because in many cases the keywords the user chooses will be different from the words the authors of the relevant documents have used. Throughout the years, many approaches have been proposed to deal with this problem. One of the most popular consists in expanding the query with related terms with the goal of retrieving more relevant documents. In this paper, we propose a new method in which a Cell Assembly model is applied for query expansion. Cell Assemblies are reverberating circuits of neurons that can persist long beyond the initial stimulus has ceased. They learn through Hebbian Learning rules and have been used to simulate the formation and the usage of human concepts. We adapted the Cell Assembly model to learn relationships between the terms in a document collection. These relationships are then used to augment the original queries. Our experiments use standard Information Retrieval test collections and show that some queries significantly improved their results with our technique.
{"title":"Cell assemblies for query expansion in Information Retrieval","authors":"Isabel Volpe, V. Moreira, C. Huyck","doi":"10.1109/IJCNN.2011.6033269","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033269","url":null,"abstract":"One of the main tasks in Information Retrieval is to match a user query to the documents that are relevant for it. This matching is challenging because in many cases the keywords the user chooses will be different from the words the authors of the relevant documents have used. Throughout the years, many approaches have been proposed to deal with this problem. One of the most popular consists in expanding the query with related terms with the goal of retrieving more relevant documents. In this paper, we propose a new method in which a Cell Assembly model is applied for query expansion. Cell Assemblies are reverberating circuits of neurons that can persist long beyond the initial stimulus has ceased. They learn through Hebbian Learning rules and have been used to simulate the formation and the usage of human concepts. We adapted the Cell Assembly model to learn relationships between the terms in a document collection. These relationships are then used to augment the original queries. Our experiments use standard Information Retrieval test collections and show that some queries significantly improved their results with our technique.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131274926","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033474
A. Alanis, E. Sánchez, E. Ruiz‐Velázquez, Blanca S. Leon
This paper presents on-line blood glucose level modeling for Type 1 Diabetes Mellitus (T1DM) patients. The model is developed using a recurrent neural network trained with an extended Kalman filter based algorithm in order to develop an affine model, which captures the nonlinear behavior of the blood glucose metabolism. The goal is to derive an on-line dynamical mathematical model of the T1DM for the response of a patient to meal and subcutaneous insulin infusion. Simulation results are utilized for identification and for testing the applicability of the proposed scheme.
{"title":"Neural model of blood glucose level for Type 1 Diabetes Mellitus Patients","authors":"A. Alanis, E. Sánchez, E. Ruiz‐Velázquez, Blanca S. Leon","doi":"10.1109/IJCNN.2011.6033474","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033474","url":null,"abstract":"This paper presents on-line blood glucose level modeling for Type 1 Diabetes Mellitus (T1DM) patients. The model is developed using a recurrent neural network trained with an extended Kalman filter based algorithm in order to develop an affine model, which captures the nonlinear behavior of the blood glucose metabolism. The goal is to derive an on-line dynamical mathematical model of the T1DM for the response of a patient to meal and subcutaneous insulin infusion. Simulation results are utilized for identification and for testing the applicability of the proposed scheme.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115711292","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033365
William J. Cukierski, Benjamin Hamner, Bo Yang
The growing ubiquity of social networks has spurred research in link prediction, which aims to predict new connections based on existing ones in the network. The 2011 IJCNN Social Network challenge asked participants to separate real edges from fake in a set of 8960 edges sampled from an anonymized, directed graph depicting a subset of relationships on Flickr. Our method incorporates 94 distinct graph features, used as input for classification with Random Forests. We present a three-pronged approach to the link prediction task, along with several novel variations on established similarity metrics. We discuss the challenges of processing a graph with more than a million nodes. We found that the best classification results were achieved through the combination of a large number of features that model different aspects of the graph structure. Our method achieved an area under the receiver-operator characteristic (ROC) curve of 0.9695, the 2nd best overall score in the competition and the best score which did not de-anonymize the dataset.
{"title":"Graph-based features for supervised link prediction","authors":"William J. Cukierski, Benjamin Hamner, Bo Yang","doi":"10.1109/IJCNN.2011.6033365","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033365","url":null,"abstract":"The growing ubiquity of social networks has spurred research in link prediction, which aims to predict new connections based on existing ones in the network. The 2011 IJCNN Social Network challenge asked participants to separate real edges from fake in a set of 8960 edges sampled from an anonymized, directed graph depicting a subset of relationships on Flickr. Our method incorporates 94 distinct graph features, used as input for classification with Random Forests. We present a three-pronged approach to the link prediction task, along with several novel variations on established similarity metrics. We discuss the challenges of processing a graph with more than a million nodes. We found that the best classification results were achieved through the combination of a large number of features that model different aspects of the graph structure. Our method achieved an area under the receiver-operator characteristic (ROC) curve of 0.9695, the 2nd best overall score in the competition and the best score which did not de-anonymize the dataset.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115726442","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033584
Sejun Kim, D. Wunsch
Hierarchical clustering is an important and powerful but computationally extensive operation. Its complexity motivates the exploration of highly parallel approaches such as Adaptive Resonance Theory (ART). Although ART has been implemented on GPU processors, this paper presents the first hierarchical ART GPU implementation we are aware of. Each ART layer is distributed in the GPU's multiprocessors and is trained simultaneously. The experimental results show that for deep trees, the GPU's performance advantage is significant.
{"title":"A GPU based Parallel Hierarchical Fuzzy ART clustering","authors":"Sejun Kim, D. Wunsch","doi":"10.1109/IJCNN.2011.6033584","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033584","url":null,"abstract":"Hierarchical clustering is an important and powerful but computationally extensive operation. Its complexity motivates the exploration of highly parallel approaches such as Adaptive Resonance Theory (ART). Although ART has been implemented on GPU processors, this paper presents the first hierarchical ART GPU implementation we are aware of. Each ART layer is distributed in the GPU's multiprocessors and is trained simultaneously. The experimental results show that for deep trees, the GPU's performance advantage is significant.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115728856","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033458
D. Ciresan, U. Meier, Jonathan Masci, J. Schmidhuber
We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rate of 99.15% by further training the nets. Our fast, fully parameterizable GPU implementation of a Convolutional Neural Network does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. A CNN/MLP committee further boosts recognition performance.
{"title":"A committee of neural networks for traffic sign classification","authors":"D. Ciresan, U. Meier, Jonathan Masci, J. Schmidhuber","doi":"10.1109/IJCNN.2011.6033458","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033458","url":null,"abstract":"We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rate of 99.15% by further training the nets. Our fast, fully parameterizable GPU implementation of a Convolutional Neural Network does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. A CNN/MLP committee further boosts recognition performance.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124103748","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033461
Tatiana Tambouratzis
A novel optical music recognition (OMR) system is put forward, where the custom-made on-screen presentation of the music score (MS) is promoted via the recognition of key music symbols only. The proposed system does not require perfect manuscript alignment or noise removal. Following the segmentation of each MS page into systems and, subsequently, into staves, staff lines, measures and candidate music symbols (CMS's), music symbol recognition is limited to the identification of the clefs, accidentals and time signatures. Such an implementation entails significantly less computational effort than that required by classic OMR systems, without an observable compromise in the quality of the on-screen presentation of the MS. The identification of the music symbols of interest is performed via probabilistic neural networks (PNN's), which are trained on a small set of exemplars from the MS itself. The initial results are promising in terms of efficiency, identification accuracy and quality of viewing.
{"title":"Identification of key music symbols for optical music recognition and on-screen presentation","authors":"Tatiana Tambouratzis","doi":"10.1109/IJCNN.2011.6033461","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033461","url":null,"abstract":"A novel optical music recognition (OMR) system is put forward, where the custom-made on-screen presentation of the music score (MS) is promoted via the recognition of key music symbols only. The proposed system does not require perfect manuscript alignment or noise removal. Following the segmentation of each MS page into systems and, subsequently, into staves, staff lines, measures and candidate music symbols (CMS's), music symbol recognition is limited to the identification of the clefs, accidentals and time signatures. Such an implementation entails significantly less computational effort than that required by classic OMR systems, without an observable compromise in the quality of the on-screen presentation of the MS. The identification of the music symbols of interest is performed via probabilistic neural networks (PNN's), which are trained on a small set of exemplars from the MS itself. The initial results are promising in terms of efficiency, identification accuracy and quality of viewing.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124359314","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033525
L. A. Silva, E. Del-Moral-Hernandez
Classification is a common task that humans perform when making a decision. Techniques of Artificial Neural Networks (ANN) or statistics are used to help in an automatic classification. This work addresses a method based in Self-Organizing Maps ANN (SOM) and K-Nearest Neighbor (KNN) statistical classifier, called SOM-KNN, applied to digits recognition in car plates. While being much faster than more traditional methods, the proposed SOM-KNN keeps competitive classification rates with respect to them. The experiments here presented contrast SOM-KNN with individual classifiers, SOM and KNN, and the results are classification rates of 89.48±5.6, 84.23±5.9 and 91.03±5.1 percent, respectively. The equivalency between SOM-KNN and KNN recognition results are confirmed with ANOVA test, which shows a p-value of 0.27.
{"title":"A SOM combined with KNN for classification task","authors":"L. A. Silva, E. Del-Moral-Hernandez","doi":"10.1109/IJCNN.2011.6033525","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033525","url":null,"abstract":"Classification is a common task that humans perform when making a decision. Techniques of Artificial Neural Networks (ANN) or statistics are used to help in an automatic classification. This work addresses a method based in Self-Organizing Maps ANN (SOM) and K-Nearest Neighbor (KNN) statistical classifier, called SOM-KNN, applied to digits recognition in car plates. While being much faster than more traditional methods, the proposed SOM-KNN keeps competitive classification rates with respect to them. The experiments here presented contrast SOM-KNN with individual classifiers, SOM and KNN, and the results are classification rates of 89.48±5.6, 84.23±5.9 and 91.03±5.1 percent, respectively. The equivalency between SOM-KNN and KNN recognition results are confirmed with ANOVA test, which shows a p-value of 0.27.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114537470","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033421
Si-Yao Fu, Guosheng Yang, Z. Hou
Ongoing efforts within neuroscience and intelligent system have been directed toward the building of artificial computational models using simulated neuron units as basic building blocks. Such efforts, inspired in the standard design of traditional neural networks, are limited by the difficulties arising from single functional performance and computational inconvenience, especially when modeling large scale, complex and dynamic processes such as cognitive recognition. Here, we show that there is a different form of implementing cortex-like mechanism, the motivation comes directly from recent pioneering works on detailed functional decomposition analysis of the visual cortex and developments on spiking neural networks (SNNs), a promising direction for neural networks, as they utilize information representation as trains of spikes, embedded with spatiotemporal characteristics. A practical implementation is presented, which can be simply described as cortical-like feed-forward hierarchy using biologically plausible neural system. As a proof of principle, a prototype model has been testified on the platform of several facial expression dataset. Of note, small structure modifications and different learning schemes allow for implementing more complicated decision system, showing great potential for discovering implicit pattern of interest and further analysis. Our results support the approach of using such hierarchical consortia as an efficient way of complex pattern analysis task not easily solvable using traditional, single functional way of implementations.
{"title":"Spiking neural networks based cortex like mechanism: A case study for facial expression recognition","authors":"Si-Yao Fu, Guosheng Yang, Z. Hou","doi":"10.1109/IJCNN.2011.6033421","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033421","url":null,"abstract":"Ongoing efforts within neuroscience and intelligent system have been directed toward the building of artificial computational models using simulated neuron units as basic building blocks. Such efforts, inspired in the standard design of traditional neural networks, are limited by the difficulties arising from single functional performance and computational inconvenience, especially when modeling large scale, complex and dynamic processes such as cognitive recognition. Here, we show that there is a different form of implementing cortex-like mechanism, the motivation comes directly from recent pioneering works on detailed functional decomposition analysis of the visual cortex and developments on spiking neural networks (SNNs), a promising direction for neural networks, as they utilize information representation as trains of spikes, embedded with spatiotemporal characteristics. A practical implementation is presented, which can be simply described as cortical-like feed-forward hierarchy using biologically plausible neural system. As a proof of principle, a prototype model has been testified on the platform of several facial expression dataset. Of note, small structure modifications and different learning schemes allow for implementing more complicated decision system, showing great potential for discovering implicit pattern of interest and further analysis. Our results support the approach of using such hierarchical consortia as an efficient way of complex pattern analysis task not easily solvable using traditional, single functional way of implementations.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114659343","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：