2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)最新文献_第6页

Development and application of an algorithm for extracting multiple linear regression equations from artificial neural networks for nonlinear regression problems 从非线性回归问题的人工神经网络中提取多元线性回归方程的算法的开发与应用

2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2016-08-01 DOI: 10.1109/ICCI-CC.2016.7862080

Veronica Chan, Christine W. Chan

{"title":"Development and application of an algorithm for extracting multiple linear regression equations from artificial neural networks for nonlinear regression problems","authors":"Veronica Chan, Christine W. Chan","doi":"10.1109/ICCI-CC.2016.7862080","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862080","url":null,"abstract":"This paper discusses the development and application of a decomposition neural network rule extraction algorithm for nonlinear regression problems, the algorithm is called the piece-wise linear artificial neural network or PWL-ANN algorithm. Rules in the form of linear equations are generated by approximating the sigmoid activation functions of the hidden neurons in an artificial neural network (ANN). The developed algorithm was applied to nineteen datasets. The preliminary results showed that the algorithm gives satisfactory results on sixteen of the nineteen tested datasets and the results demonstrate high fidelity to the originally trained neural network models. By analyzing the values of R2 given by the PWL approximation on the hidden neurons and the overall output, it is evident that there are more factors affecting the fidelity of the algorithm apart from the precision of the approximation of each individual node of the given ANN model. Nevertheless, the algorithm shows promising potential for application in engineering problems.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130912489","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: 9

Segmentation of nuclei in digital pathology images 数字病理图像中核的分割

2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2016-08-01 DOI: 10.1109/ICCI-CC.2016.7862091

P. Guo, A. Evans, P. Bhattacharya

引用次数: 16

A new multifunctional neural network with high performance and low energy consumption 一种新型高性能、低能耗的多功能神经网络

2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2016-08-01 DOI: 10.1109/ICCI-CC.2016.7862082

L. M. Zhang

{"title":"A new multifunctional neural network with high performance and low energy consumption","authors":"L. M. Zhang","doi":"10.1109/ICCI-CC.2016.7862082","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862082","url":null,"abstract":"A common artificial neural network (ANN) uses the same activation function for all hidden and output neurons. Therefore, it has an optimization limitation for complex big data analysis due to its single mathematical functionality. In addition, an ANN with a complicated activation function uses a very long training time and consumes a lot of energy. To address these issues, this paper presents a new energy-efficient “Multifunctional Neural Network” (MNN) that uses a variety of different activation functions to effectively improve performance and significantly reduce energy consumption. A generic training algorithm is designed to optimize the weights, biases, and function selections for improving performance while still achieving relatively fast computational time and reducing energy usage. A novel general learning algorithm is developed to train the new energy-efficient MNN. For performance analysis, a new “Genetic Deep Multifunctional Neural Network” (GDMNN) uses genetic algorithms to optimize the weights and biases, and selects the set of best-performing energy-efficient activation functions for all neurons. The results from sufficient simulations indicate that this optimized GDMNN can perform better than other GDMNNs in terms of achieving high performance (prediction accuracy), low energy consumption, and fast training time. Future works include (1) developing more effective energy-efficient learning algorithms for the MNN for data mining application problems, and (2) using parallel cloud computing methods to significantly speed up training the MNN.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127359529","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

Learnings and innovations in speech recognition 语音识别的学习和创新

2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2016-08-01 DOI: 10.1109/ICCI-CC.2016.7862097

F. Beaufays

引用次数: 0

Logical consensuses for case-based reasoning and for mathematical engineering of AI 基于案例推理和人工智能数学工程的逻辑共识

2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2016-08-01 DOI: 10.1109/ICCI-CC.2016.7862041

É. Grégoire, Jean-Marie Lagniez, Du Zhang

引用次数: 1

Techniques for cognition of driving context for safe driving application 驾驶环境认知技术在安全驾驶中的应用

2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2016-08-01 DOI: 10.1109/ICCI-CC.2016.7862066

Giacomo Briochi, M. Colombetti, M. D. Hina, Assia Soukane, A. Ramdane-Cherif

引用次数: 4

Ranking preferences deduction based on semantic similarity for the stable marriage problem 基于语义相似度的稳定婚姻问题排序偏好演绎

2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2016-08-01 DOI: 10.1109/ICCI-CC.2016.7862088

Michaël Guedj

引用次数: 1

Disaster-aware smart routing scheme based on symbiotic computing for highly-available information storage systems 基于共生计算的高可用性信息存储系统容灾智能路由方案

2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2016-08-01 DOI: 10.1109/ICCI-CC.2016.7862026

S. Izumi, Asato Edo, Toru Abe, T. Suganuma

引用次数: 1

Semantic computing of simplicity in attributed generalized trees 属性广义树中简单性的语义计算

2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2016-08-01 DOI: 10.1109/ICCI-CC.2016.7862043

Mahsa Kiani, V. Bhavsar, H. Boley

引用次数: 1

An information theoretic criterion for adaptive multiobjective memetic optimization 自适应多目标模因优化的信息论准则

2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2016-08-01 DOI: 10.1109/ICCI-CC.2016.7862030

Hieu V. Dang, W. Kinsner

引用次数: 2