Proceedings of the 19th International Conference on Computer Systems and Technologies最新文献

筛选

英文中文

Proceedings of the 19th International Conference on Computer Systems and Technologies 第19届计算机系统与技术国际会议论文集

Proceedings of the 19th International Conference on Computer Systems and Technologies Pub Date : 2018-09-13 DOI: 10.1145/3274005

引用次数: 0

Deep Learning in Spiking Neural Networks for Brain-Inspired Artificial Intelligence 脑启发人工智能中脉冲神经网络的深度学习

Proceedings of the 19th International Conference on Computer Systems and Technologies Pub Date : 2018-09-13 DOI: 10.1145/3274005.3274006

N. Kasabov

{"title":"Deep Learning in Spiking Neural Networks for Brain-Inspired Artificial Intelligence","authors":"N. Kasabov","doi":"10.1145/3274005.3274006","DOIUrl":"https://doi.org/10.1145/3274005.3274006","url":null,"abstract":"Brain-inspired AI (BI-AI) is the contemporary phase in the AI development that is concerned with the design and implementation of highly intelligent machines that utilise information processing principles from the human brain, along with their applications. Artificial neural networks (ANN), in their early developments world-wide (the first publication in Bulgarian was in 1990 [1] and then [2, 3])) were promising techniques for AI from the very beginning. But their full potential is just being realised through the latest brain-inspired spiking neural networks (SNN) and their deep learning algorithms, that make it possible for AI to gain a fast progress nowadays [3-14]. This presentation has two parts. The first part covers generic methodological aspects of AI and neural networks, including: Learning evolving processes in space and time; Data, Information and Knowledge; The human brain as a deep learning system; Classical methods of ANN; Methods of SNN; Deep learning in brain-inspired SNN architectures; Evolutionary and quantum-inspired optimisation of SNN systems. The second part presents specific methods, systems and applications based on deep learning in SNN and BI-AI for various problems and data, including audio/visual data, brain EEG and fMRI data, Brain-Computer Interfaces (BCI), Bio/Neuroinformatics data, Multisensory data for predictive modelling in ecology, environment, finance. It concludes with discussions about the future of computers and AI. A development software system NeuCube and application systems can be found on: http://www.kedri.aut.ac.nz/neucube/. Details of this presentation are included in [15].","PeriodicalId":152033,"journal":{"name":"Proceedings of the 19th International Conference on Computer Systems and Technologies","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132843056","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

Performance Evaluation of Deep Learning Networks for Semantic Segmentation of Traffic Stereo-Pair Images 交通立体对图像语义分割的深度学习网络性能评价

Proceedings of the 19th International Conference on Computer Systems and Technologies Pub Date : 2018-06-05 DOI: 10.1145/3274005.3274032

Vlad Taran, N. Gordienko, Yuriy Kochura, Yuri G. Gordienko, Oleksandr Rokovyi, Oleg Alienin, S. Stirenko

{"title":"Performance Evaluation of Deep Learning Networks for Semantic Segmentation of Traffic Stereo-Pair Images","authors":"Vlad Taran, N. Gordienko, Yuriy Kochura, Yuri G. Gordienko, Oleksandr Rokovyi, Oleg Alienin, S. Stirenko","doi":"10.1145/3274005.3274032","DOIUrl":"https://doi.org/10.1145/3274005.3274032","url":null,"abstract":"Semantic image segmentation is one the most demanding task, especially for analysis of traffic conditions for self-driving cars. Here the results of application of several deep learning architectures (PSPNet and ICNet) for semantic image segmentation of traffic stereo-pair images are presented. The images from Cityscapes dataset and custom urban images were analyzed as to the segmentation accuracy and image inference time. For the models pre-trained on Cityscapes dataset, the inference time was equal in the limits of standard deviation, but the segmentation accuracy was different for various cities and stereo channels even. The distributions of accuracy (mean intersection over union - mIoU) values for each city and channel are asymmetric, long-tailed, and have many extreme outliers, especially for PSPNet network in comparison to ICNet network. Some statistical properties of these distributions (skewness, kurtosis) allow us to distinguish these two networks and open the question about relations between architecture of deep learning networks and statistical distribution of the predicted results (mIoU here). The results obtained demonstrated the different sensitivity of these networks to: (1) the local street view peculiarities in different cities that should be taken into account during the targeted fine tuning the models before their practical applications, (2) the right and left data channels in stereo-pairs. For both networks, the difference in the predicted results (mIoU here) for the right and left data channels in stereo-pairs is out of the limits of statistical error in relation to mIoU values. It means that the traffic stereo pairs can be effectively used not only for depth calculations (as it is usually used), but also as an additional data channel that can provide much more information about scene objects than simple duplication of the same street view images.","PeriodicalId":152033,"journal":{"name":"Proceedings of the 19th International Conference on Computer Systems and Technologies","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122003895","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: 7

首页上一页