Proceedings of the International Joint Conference on Neural Networks, 2003.最新文献_第3页

Retina encoder tuning and data encryption for learning retina implants 视网膜编码器调整和数据加密学习视网膜植入物

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223872

O. Baruth, R. Eckmiller, D. Neumann

{"title":"Retina encoder tuning and data encryption for learning retina implants","authors":"O. Baruth, R. Eckmiller, D. Neumann","doi":"10.1109/IJCNN.2003.1223872","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223872","url":null,"abstract":"A retina encoder (RE) as part of a visual prosthesis (retina implant) for blind subjects with retinal degenerative disorders was implemented by an array of 256 tunable spatio-temporal filters (ST) to map visual patterns P1 onto encoded output patterns as functional approximation of retina information processing. These RE-output signals were fed into a visual system module (VM) to simulate the mapping (by the central visual system) of the retinal output onto visual percepts P2, which were visualized on a monitor. Alternative tuning strategies for roaming within the large spatio-temporal state space of RE were developed and tested. Initially, VM as neural network was trained to generate a P2 very similar to a selected set of P1s by feeding the corresponding RE-outputs into VM. RE tuning was tested by presenting a given small set of P1s to the serial coupling of RE and VM and by monitoring a modified Hamming distance between P2 and P1, while the ST-parameters were tuned. Human volunteers with normal vision were asked to approximate P2 to P1 directly, with random search, or by means of a dialog-based tuning with an evolutionary algorithm (EA). Typically, dialog-based EA tuning reached the optimal similarity between P2 and P1 (limited by the quality of VM) within less than 200 iterations. In contrast, manual tuning required considerably more iteration steps and converged to a smaller similarity between P2 and P1. Structure and function of our tunable RE offer not only an optimization of visual perception, but may also be important to serve as technical encryption unit (EU) in connection with the human central visual system as biological decryption unit (DU); an important feature to meet the authentication requirements of active medical devices.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126814938","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: 5

Genetic learning of functional link networks 功能链接网络的遗传学习

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223385

C. Bhumireddy, C. Chen

引用次数: 5

Two-cell cellular neural networks: generation of new hyperchaotic multiscroll attractors 双细胞神经网络:新一代超混沌多涡旋吸引子

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223814

D. Cafagna, G. Grassi

引用次数: 6

Robust recognition based on adaptive combination of weak classifiers 基于弱分类器自适应组合的鲁棒识别

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223765

Guoping Wang, M. Pavel, Xubo B. Song

引用次数: 2

Processing of analogy in the thalamocortical circuit 丘脑皮层回路中类比的处理

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223916

Y. Choe

引用次数: 3

Neural net with two hidden layers for non-linear blind source separation 非线性盲源分离的两隐层神经网络

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223461

R. Martín-Clemente, S. Hornillo-Mellado, J. I. Acha, F. R. Ruiz, C. Puntonet

引用次数: 0

Feature selection assessment and comparison using two saliency measures in an Elman recurrent neural network Elman递归神经网络中两种显著性度量的特征选择评估与比较

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1224016

T. I. Laine, K. Bauer

{"title":"Feature selection assessment and comparison using two saliency measures in an Elman recurrent neural network","authors":"T. I. Laine, K. Bauer","doi":"10.1109/IJCNN.2003.1224016","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1224016","url":null,"abstract":"This paper provides a summary of a feasibility study conducted to assess and compare a weight based and a network output sensitivity based saliency measure for use with an Elman recurrent neural network (RNN). An experiment was designed to assign temporal data with significant noise, autocorrelation and crosscorrelation into one of two classes. To improve classification accuracy, feature saliency screening was performed to select a subset of the eight candidate input features using a weight based signal-to-noise ratio and an output sensitivity based measure. With consistent selection and ranking of features observed between the two saliency measures, both indicated a parsimonious subset of three of the original eight input features should be retained. Using CPU time as a surrogate measure of operations required, the computational efficiency was also found equivalent, with an observed difference of less than 2.5% between methods. Numerical results show a parsimonious subset of features improved generalization by significantly reducing the classification accuracy variance for multiple data sets and trained RNNs across time periods. An increase in classification accuracy for the last time period was even obtained for an independent validation set using the reduced feature set.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116342863","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: 5

The role of temporal coding in the processing of relational information in the mind-brain 时间编码在脑-脑关系信息处理中的作用

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223897

L. Shastri

引用次数: 3

Feature guided visual attention with topographic array processing and neural network-based classification 基于地形阵列处理和神经网络分类的特征引导视觉注意

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223918

G. Tímár, D. Bálya, I. Szatmári, C. Rekeczky

引用次数: 7

Incremental learning in dynamic environments using neural network with long-term memory 基于长期记忆的神经网络在动态环境中的增量学习

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223973

K. Tsumori, S. Ozawa

{"title":"Incremental learning in dynamic environments using neural network with long-term memory","authors":"K. Tsumori, S. Ozawa","doi":"10.1109/IJCNN.2003.1223973","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223973","url":null,"abstract":"When the environment is dynamically changed for agents, knowledge acquired from an environment might be useless in the future environments. Therefore, agents should not only acquire new knowledge but also modify or delete old knowledge. However, these modification and deletion are not always efficient in learning. Because the knowledge once acquired in the past can be useful again in the future when the same environment reappears. To learn efficiently in this situation, agents should have memory to store old knowledge. In this paper, we propose an agent architecture that consists of four modules: resource allocating network (PAN), long-term memory (LTM), association buffer (A-Buffer), and environmental change detector (ECD). In LTM, not only acquired knowledge but also the information about which knowledge was produced in the same environment is stored. This information is utilized for recalling the knowledge acquired in the past when the same environment reappears. To evaluate the adaptability in a class of dynamic environments, we apply this model to a simple problem that some target functions to be approximated are changed in turn. As a result, we verify the following adaptability of RAN-ALTM: (1) incremental learning can be stably carried out, (2) environmental changes are correctly detected, (3) fast adaptation is realized by training some of the accumulated knowledge when the past environments reappear.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126019714","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: 13