发布求助
文献互助 智能选刊 最新文献

2016 International Joint Conference on Neural Networks (IJCNN)最新文献

筛选
英文 中文
A hardware-efficient multi-compartment soma-dendrite model based on asynchronous cellular automaton dynamics 基于异步元胞自动机动力学的多室体-树突模型
2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727202
Narutoshi Jodai, H. Torikai
{"title":"A hardware-efficient multi-compartment soma-dendrite model based on asynchronous cellular automaton dynamics","authors":"Narutoshi Jodai, H. Torikai","doi":"10.1109/IJCNN.2016.7727202","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727202","url":null,"abstract":"In this paper, a multi-compartment soma-dendrite model based on asynchronous cellular automaton dynamics is designed. It is shown that the model can reproduce typical propagation phenomena of membrane potentials between somas and dendrites of neurons. Also, the model is implemented in a field programmable gate array and it is shown that the model can be implemented by using much less hardware resource compared to conventional multi-compartment soma-dendrite models.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125819339","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}
引用次数: 1
Deep Self-Organising Maps for efficient heterogeneous biomedical signatures extraction 高效异构生物医学特征提取的深度自组织映射
2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727869
Nataliya Sokolovska, N. Hai, K. Clément, Jean-Daniel Zucker
{"title":"Deep Self-Organising Maps for efficient heterogeneous biomedical signatures extraction","authors":"Nataliya Sokolovska, N. Hai, K. Clément, Jean-Daniel Zucker","doi":"10.1109/IJCNN.2016.7727869","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727869","url":null,"abstract":"Feature selection is used to preserve significant properties of data in a compact space. In particular, feature selection is needed in applications, where information comes from multiple heterogeneous high dimensional sources. Data integration, however, is a challenge in itself. In our contribution, we introduce a feature selection framework based on powerful visualisation capabilities of self-organising maps, where the deep structure can be learned in a supervised or unsupervised manner. For a supervised version of the deep SOM, we propose to carry out inference with a linear SVM. A forward-backward procedure helps to converge to an optimal feature set. We show by experiments on real large-scale biomedical data set that the proposed methods embed data in a new compact meaningful representation, allow to visualise biomedical signatures, and also lead to a reasonable classification accuracy compared to the state-of-the-art methods.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123559998","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}
引用次数: 2
Sentiment classification using Comprehensive Attention Recurrent models 基于综合注意循环模型的情感分类
2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727384
Yong Zhang, M. Er, R. Venkatesan, Ning Wang, Mahardhika Pratama
{"title":"Sentiment classification using Comprehensive Attention Recurrent models","authors":"Yong Zhang, M. Er, R. Venkatesan, Ning Wang, Mahardhika Pratama","doi":"10.1109/IJCNN.2016.7727384","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727384","url":null,"abstract":"Sentiment classification has been a very hot topic in the field of natural language processing (NLP) and understanding in recent years. Recurrent neural networks (RNN) is a widely used tool to deal with the classification problem of variable-length sentences. The standard RNN can only access the preceding context of a sentence. In this paper, a new architecture termed Comprehensive Attention Recurrent Neural Networks (CA-RNN) which can store preceding, succeeding and local contexts of any position in a sequence is developed. The bidirectional recurrent neural networks (BRNN) is used to access the past and future information while a convolutional layer is employed to capture local information. The standard RNN is also replaced by two recently emerged RNN variants, namely long short-term memory (LSTM) and gated recurrent unit (GRU), to enhance the effectiveness of the new architecture. Another salient feature of the proposed model is that it can be trained end-to-end without any human intervention. It is very easy to be implemented. We conduct experiments on several sentiment-labeled datasets and analysis tasks. Experiment results demonstrate that capturing comprehensive contextual information can significantly enhance the classification accuracy compared with the standard recurrent models and the new models can achieve competitive performance compared with the state-of-the-art approaches.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123599206","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}
引用次数: 46
Gödel vs. aristotle: Algorithmic complexity, models of the Mind, and top representations Gödel vs.亚里士多德:算法复杂性、心智模型和顶级表征
2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727416
L. Perlovsky
{"title":"Gödel vs. aristotle: Algorithmic complexity, models of the Mind, and top representations","authors":"L. Perlovsky","doi":"10.1109/IJCNN.2016.7727416","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727416","url":null,"abstract":"Brains learn much better than computers. But why? Is there a fundamental reason behind computers being slow learners? Often slow learning is described as computational complexity. This paper discusses that complexity of algorithms is as fundamental as Gödelian incompleteness of logic. Although the Gödel's theory is well recognized, its significance for engineering and modeling of the mind has not been appreciated. The mind-brain overcomes this fundamental difficulty, why computers cannot? I emphasize here that the reason is logical bases of machine learning. Aristotle explained that mind is not logical. The paper discusses that most neural networks and fuzzy systems require logical steps. A “nonlogical” mathematical theory overcoming computational complexity is described. It turns out to closely follow Aristotle's ideas. The new theory explains contents of the highest representations in the mind hierarchy, and related aesthetic emotions revealing the nature of the beautiful and the meaning of life. I discuss how it is possible that a non-logical mathematical technique can be computable, the function of logic in the mind, its relation to consciousness, and difficulties of understanding unconscious mechanisms.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125532755","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}
引用次数: 2
Precise 2D point set registration using iterative closest algorithm and correntropy 基于迭代最接近算法和相关系数的精确二维点集配准
2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727806
Guanglin Xu, S. Du, Jianru Xue
{"title":"Precise 2D point set registration using iterative closest algorithm and correntropy","authors":"Guanglin Xu, S. Du, Jianru Xue","doi":"10.1109/IJCNN.2016.7727806","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727806","url":null,"abstract":"The iterative closest point (ICP) algorithm is fast and accurate for rigid point set registration, but it works badly when there are many outliers and noises in the point sets. This paper instead proposes a novel method based on the ICP algorithm to deal with this problem. Firstly, correntropy is introduced into the rigid registration problem and then a new energy function based on maximum correntropy criterion is proposed. After that, a new ICP algorithm based on correntropy is proposed, which performs well in dealing with rigid registration with noises and outliers. This new algorithm converges moronically from any given parameters, which is similar to the ICP algorithm. Experimental results demonstrate its accuracy and efficiency compared with the traditional ICP algorithm.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125553198","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}
引用次数: 22
Assessing diffusion of spatial features in Deep Belief Networks 深度信念网络中空间特征的扩散评估
2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727392
H. Tosun, B. Mitchell, John W. Sheppard
{"title":"Assessing diffusion of spatial features in Deep Belief Networks","authors":"H. Tosun, B. Mitchell, John W. Sheppard","doi":"10.1109/IJCNN.2016.7727392","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727392","url":null,"abstract":"Deep learning has recently gained popularity in many machine learning applications, but a theoretical grounding for the strengths, weaknesses, and implicit biases of various deep learning methods is still a work in progress. Here, we analyze the role of spatial locality in Deep Belief Networks (DBN) and show that spatially local information is lost through diffusion as the network becomes deeper. We then analyze an approach we developed previously, based on partitioning of Restricted Boltzmann Machines (RBMs), to demonstrate that our method is capable of retaining spatially local information when training DBNs. Specifically, we find that spatially local features are completely lost in DBNs trained using the “standard” RBM method, but are largely preserved using our partitioned training method. In addition, reconstruction accuracy of the model is improved using our Partitioned-RBM training method.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115055103","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}
引用次数: 3
A conceptual modeling of flocking-regulated multi-agent reinforcement learning 群集调节多智能体强化学习的概念建模
2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727894
C. S. Chen, Yaqing Hou, Y. Ong
{"title":"A conceptual modeling of flocking-regulated multi-agent reinforcement learning","authors":"C. S. Chen, Yaqing Hou, Y. Ong","doi":"10.1109/IJCNN.2016.7727894","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727894","url":null,"abstract":"In this paper, we present a multi-agent reinforcement learning (MARL) framework that leverages the emergent behaviors from swarm intelligence (SI). The essential backbone of our framework is an flocking-regulated cooperative learning paradigm in which the cooperation among learning agents is realized via the self-organizing principles derived from natural interaction of flocking boids. In the proposed MARL, each reinforcement learner learns and evolves in the dynamic environment, and is steered by flocking behavior rules such as cohesion, separation, alignment, fear, etcs. The use of the flocking rules provides distributed sensing and communication content for the cooperation of multiple learning agents in the context of pursuit game. The effectiveness of the MARL framework is studied by its application of the multi-agent pursuit game.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115481999","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}
引用次数: 4
A digital neuromorphic circuit for neural-glial interaction 神经-胶质相互作用的数字神经形态电路
2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727201
S. Gomar, M. Mirhassani, M. Ahmadi, M. Saif
{"title":"A digital neuromorphic circuit for neural-glial interaction","authors":"S. Gomar, M. Mirhassani, M. Ahmadi, M. Saif","doi":"10.1109/IJCNN.2016.7727201","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727201","url":null,"abstract":"Astrocyte as one of the brain cells controls synaptic activity between neurons by providing feedback to neurons. A novel digital hardware is proposed for neuron-synapse-astrocyte network based on the biological Adaptive Exponential (AdEx) neuron and Postnov astrocyte cell model. The network can be used for implementation of large scale spiking neural networks. Synthesis of the designed circuits shows that the designed astrocyte circuit is able to imitate its biological model and regulate the synapse transmission, successfully. In addition, synthesis results confirms that the proposed design uses less than 1% of available resources of a VIRTEX II FPGA which saves up to 4.4% of FPGA resources in comparison to other designs.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116424117","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}
引用次数: 4
Exploring deep features from brain tumor magnetic resonance images via transfer learning 通过迁移学习探索脑肿瘤磁共振图像的深层特征
2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727204
Renhao Liu, L. Hall, Dmitry Goldgof, Mu Zhou, R. Gatenby, K. B. Ahmed
{"title":"Exploring deep features from brain tumor magnetic resonance images via transfer learning","authors":"Renhao Liu, L. Hall, Dmitry Goldgof, Mu Zhou, R. Gatenby, K. B. Ahmed","doi":"10.1109/IJCNN.2016.7727204","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727204","url":null,"abstract":"Finding appropriate feature representations from radiological images is a vital task for prediction and diagnosis. Deep convolutional neural networks have recently achieved state-of-the-art performance in classification problems from several different domains. Research has also shown the feasibility of using a pre-trained deep neural network as a feature extractor when only a small dataset is available. This paper proposes a novel image feature extraction method for predicting survival time from brain tumor magnetic resonance images using pretrained deep neural networks. Since all tumors are different sizes, we also explore different image resizing methods in the paper. We demonstrate that deep features can result in better survival time prediction with the highest accuracy of 95.45% versus conventional feature extraction methods from magnetic resonance images of the brain.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116557247","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}
引用次数: 25
On the synergism of evolutionary neuro-fuzzy system 论进化神经模糊系统的协同作用
2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727834
Vivek Srivastava, B. Tripathi, V. Pathak, Anand Tiwari
{"title":"On the synergism of evolutionary neuro-fuzzy system","authors":"Vivek Srivastava, B. Tripathi, V. Pathak, Anand Tiwari","doi":"10.1109/IJCNN.2016.7727834","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727834","url":null,"abstract":"In the recent past, it has been seen that the synergism of evolutionary, fuzzy and neural network is gaining popularity over individual techniques due to its combined computational efficiency. In this paper, we have investigated the feasibility of synergism between evolutionary fuzzy clustering using three different validity criteria and neural networks. We have also reported the effect of various parameters such as fuzzifier, outlier control and generalization parameter over system performance. Here, all the variants of evolutionary fuzzy clustering are employed for structure selection and learning of neural network. Performance evaluation has been carried out over wide spectrum of benchmark problems and biometric recognition problems. Experimental results demonstrate the comparative analysis of synergism of evolutionary fuzzy clustering with neural network. It has been found that evolutionary fuzzy clustering using Xie Beni criteria with neural network outperforms over other variants. Also, evolutionary fuzzy clustering combined with neural network performs far better than the synergism of fuzzy clustering with neural network. We have obtained promising results even for biometric datasets including eye-movement, face and periocular biometrics.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122776581","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}
引用次数: 1
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信