Filters








2,050 Hits in 3.7 sec

Resource-Efficient Neural Networks for Embedded Systems [article]

Wolfgang Roth, Günther Schindler, Matthias Zöhrer, Lukas Pfeifenberger, Robert Peharz, Sebastian Tschiatschek, Holger Fröning, Franz Pernkopf, Zoubin Ghahramani
2020 arXiv   pre-print
with virtually unlimited computing resources into every day's applications.  ...  The development of such approaches is among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning technology from a scientific environment  ...  We acknowledge NVIDIA for providing GPU computing resources. References Jan Achterhold, Jan M. Köhler, Anke Schmeink, and Tim Genewein. Variational network quantization.  ... 
arXiv:2001.03048v1 fatcat:w5ubaeakwjfifbmj6fwxl4gzqu

Advanced applications of APL: logic programming, neural networks, and hypertext

M. Alfonseca
1991 IBM Systems Journal  
But even this space IBM SYSTEMS JOURNAL, VOL 30, NO 4, 1991 problem can be solved, as the network connectivity matrices contain many zeros, and an implementa- tion of sparse matrices can be used to make  ...  IBM SYSTEMS JOURNAL, VOL 30, NO 4, 1991 A neural network wh-re at least one neuron sends a connection to another neuron in a preceding layer is a neural network with feedback.  ... 
doi:10.1147/sj.304.0543 fatcat:bpu3nvyahzhcflpbklqmyodnsi

Recommender systems

Linyuan Lü, Matúš Medo, Chi Ho Yeung, Yi-Cheng Zhang, Zi-Ke Zhang, Tao Zhou
2012 Physics reports  
In addition to algorithms, physical aspects are described to illustrate macroscopic behavior of recommender systems. Potential impacts and future directions are discussed.  ...  Extensive research for recommender systems is conducted by a broad range of communities including social and computer scientists, physicists, and interdisciplinary researchers.  ...  It would be very misleading to think that recommender systems are studied only because suitable data sets are available.  ... 
doi:10.1016/j.physrep.2012.02.006 fatcat:cywkeyu2wjdzhdqkg2545v5f7a

Comparison of Flight Control System Design Methods in Landing [chapter]

S.H. Sadati, M.Sabzeh Parvar, M.B. Menhaj
2011 Advances in Flight Control Systems  
Neural Net-based Control Design Artificial neural networks are circuits, computer algorithms, or mathematical representations loosely inspired by the massively connected set of neurons that form biological  ...  Fuzzy Logic-Based Control Design The existing applications of fuzzy control range from micro-controller based systems in home applications to advanced flight control systems.  ...  The aim of the book Advances in Flight Control Systems is to bring together reputable researchers from different countries in order to provide a comprehensive coverage of advanced and modern topics in  ... 
doi:10.5772/15596 fatcat:ejh3oim44vbwrov7aq3ghwtzdu

Design of an Intelligent Symptom Differentiation and Electrical Stimulation Rehabilitation System

Jiali Liu, Kai Li
2020 Journal Europeen des Systemes Automatises  
The proposed system was applied to treat 30 patients with primary insomnia in the sleep center of a tertiary hospital.  ...  The system was designed with the aid of the following technologies: fuzzy analytic hierarchy process (AHP), chromatographic decomposition, spatiotemporal slicing, optical flow field method, collaborative  ...  SYSTEM REALIZATION The proposed ISD-ESR system aims to provide the patient with suitable electric stimulation prescriptions from the knowledge base, according to his/her health data extracted from face  ... 
doi:10.18280/jesa.530511 fatcat:awfs33xe7jhixikskiwhgst7oa

Research on Basketball Teaching Network Course Resource Recommendation Method Based on Deep Learning Algorithm

Kai Ma, Fazlullah Khan
2021 Mobile Information Systems  
Experimental results show that the proposed model achieved the lowest computation time of 15 s and recommendation error less than 0.4% as compared with the existing model.  ...  To validate the performance, the proposed model was compared with two well-known recommendation models such as the learning resource recommendation method based on transfer learning and the personalized  ...  It utilizes graph technologies with transformations among neurons to develop many-layered learning models.  ... 
doi:10.1155/2021/3256135 fatcat:iqtr2opn75coxo75exkgggulfm

COMPARISON OF FLIGHT CONTROL SYSTEM DESIGN METHODS IN LANDING

S. H. Sadati, M. Sabzeh Parvar, M. B. Menhaj
2010 Asian journal of control  
Neural Net-based Control Design Artificial neural networks are circuits, computer algorithms, or mathematical representations loosely inspired by the massively connected set of neurons that form biological  ...  Fuzzy Logic-Based Control Design The existing applications of fuzzy control range from micro-controller based systems in home applications to advanced flight control systems.  ...  The aim of the book Advances in Flight Control Systems is to bring together reputable researchers from different countries in order to provide a comprehensive coverage of advanced and modern topics in  ... 
doi:10.1111/j.1934-6093.2007.tb00439.x fatcat:ftgqbwbi2fc3fl375wrarxa67i

MASECO: A Multi-agent System for Evaluation and Classification of OERs and OCW Based on Quality Criteria [chapter]

Gabriela Moise, Monica Vladoiu, Zoran Constantinescu
2013 Studies in Computational Intelligence  
The Communication Agent corroborates information from the OER/OCW Management System and sends it together with the user's needs to the OER/OCW Classification Agent, which returns a result to the Communication  ...  value of digital resources, which is understandable taking into account that this capacity to evaluate and discriminate lays on the highest level of critical thinking skill in Bloom's taxonomy for thinking  ...  The authors are very grateful to both the editors and the anonymous reviewers for their valuable comments and ideas to improve this chapter.  ... 
doi:10.1007/978-3-642-41965-2_7 fatcat:gmuxwlgfprfedkiqsq3szsaipi

Detecting Control System Misbehavior by Fingerprinting Programmable Logic Controller Functionality

Melissa Stockman, Dipankar Dwivedi, Reinhard Gentz, Sean Peisert
2019 International Journal of Critical Infrastructure Protection  
and end signatures in noisy measurement data. 49 In computing, power analysis was one of the first methods to extract hidden 50 information from computing devices.  ...  In addition, computation stages have been 52 derived from power analysis [8].  ... 
doi:10.1016/j.ijcip.2019.100306 fatcat:vfr5r7siknbenjqbou7bq4u4ia

SecureML: A System for Scalable Privacy-Preserving Machine Learning

Payman Mohassel, Yupeng Zhang
2017 2017 IEEE Symposium on Security and Privacy (SP)  
of data samples with thousands of features.  ...  We implement our system in C++.  ...  Acknowledgements We thank Jing Huang from Visa Research for helpful discussions on machine learning, and Xiao Wang from University of Maryland for his help on the EMP toolkit.  ... 
doi:10.1109/sp.2017.12 dblp:conf/sp/MohasselZ17 fatcat:y6lwerwfwnfghjkia76yqenmiy

Neural networks for decision support:

Shimon Schocken, Gad Ariav
1994 Decision Support Systems  
Neural networks offer an approach to computing whichunlike conventional programmingdoes not necessitate a complete algorithmic specification.  ...  Incidentally, these have also been some of the fundamental motivations for the development of decision support systems in general.  ...  The DSS framework was designed with one objective in mind: help researchers and practitioners think systematically about the many factors that come to play in the design and use of decision support systems  ... 
doi:10.1016/0167-9236(94)90015-9 fatcat:jkmu3atnqfambjduxo5lbzuo7i

Technical Target Setting in QFD for Web Service Systems Using an Artificial Neural Network

Lianzhang Zhu, Xiaowing Liu
2010 IEEE Transactions on Services Computing  
There are at least two challenges with quality management of service-oriented architecture based web service systems: 1) how to link its technical capabilities with customer's needs explicitly to satisfy  ...  In this paper, we analyze requirements for web services and their design attributes, and apply the QFD for developing web service systems by linking quality of service requirements to web service design  ...  To the enterprise manager, service orientation is a means for effectively integrating the diverse systems typical of modern enterprise data centers.  ... 
doi:10.1109/tsc.2010.45 fatcat:xjhven7i2fbo3arptnxnaa2xnm

Research on Classroom Teaching Evaluation and Instruction System Based on GIS Mobile Terminal

Jing Zhang, Sang-Bing Tsai
2021 Mobile Information Systems  
Among them, after adopting the teaching evaluation system of GIS mobile terminal, the number of students who thought the teaching evaluation system was useless dropped from 4.6% to 1.8%.  ...  With the development of mobile terminal technology, GIS has begun to be applied in all walks of life.  ...  It is recommended to interact with the system status information in real time, such as the user's login status and report push and sharing, improve the interaction between the system and the user, and  ... 
doi:10.1155/2021/9790766 fatcat:fb7hqm3i7vcwnbqidyrizra5uy

Comparison of Zero Replacement Strategies for Compositional Data with Large Numbers of Zeros

Sugnet Lubbe, Peter Filzmoser, Matthias Templ
2021 Chemometrics and Intelligent Laboratory Systems  
Modern applications in chemometrics and bioinformatics result in compositional data sets with a high proportion of zeros.  ...  Different replacement techniques from compositional data analysis are considered and compared by a simulation study and examples.  ...  , dropout ¼ 0.1, 10 layers starting with 1000 neurons).  ... 
doi:10.1016/j.chemolab.2021.104248 fatcat:kasuznzizra67iurdeh3l6mepi

Intelligent Systems: Architectures and Perspectives [chapter]

Ajith Abraham
2003 Studies in Fuzziness and Soft Computing  
years, contributed to a large number of new intelligent system designs.  ...  An important advantage of probabilistic reasoning is its ability to update previous outcome estimates by conditioning them with newly available evidence [57].  ...  Acknowledgements Author is grateful to Professor Lakhmi Jain (University of South Australia, Adelaide) and the three referees for the technical comments, which improved the clarity of this chapter.  ... 
doi:10.1007/978-3-7908-1770-6_1 fatcat:u7g7qckslzcyxnxghenpzuwpma
« Previous Showing results 1 — 15 out of 2,050 results