Refine
Document Type
- Part of Periodical (13) (remove)
Language
- English (13) (remove)
Keywords
- computer clusters (3)
- artificial neural networks (2)
- classification (2)
- parallel algorithms (2)
- Adaptive Services Grid (ASG) (1)
- COVID-19 (1)
- Cloud Computing (1)
- Computer Supported Cooperative Work (1)
- Enterprise Systems (1)
- Heimarbeit (1)
- IT Outsourcing (1)
- IT Security (1)
- IT Services (1)
- Internet Voting (1)
- ODRL (1)
- OWL (1)
- RDF (1)
- Security (1)
- Semantic Web (1)
- Service-oriented Architectures (SOA) (1)
- Telearbeit (1)
- Umfrage (1)
- adaptive resonance theory (1)
- artifcial neural networks (1)
- artififfcial neural networks (1)
- assessment model (1)
- blood analysis (1)
- categorisation (1)
- digital workplace (1)
- e-service (1)
- e-service quality (1)
- estimation of algorithm efficiency (1)
- governance (1)
- gradient method of training weight coefficients (1)
- hybrid work (1)
- information system (1)
- mathematical model (1)
- methodology (1)
- minimum self-contained graphs (1)
- parallel calculations (1)
- regression analysis (1)
- remote work (1)
- risk (1)
- social media (1)
- social object (1)
- social simulation (1)
- virtual goods (1)
- web-portal medical e-services (1)
- work from anywhere (1)
- work from home (1)
Institute
- Institut für Wirtschafts- und Verwaltungsinformatik (13) (remove)
An estimation of the number of multiplication and addition operations for training artififfcial neural networks by means of consecutive and parallel algorithms on a computer cluster is carried out. The evaluation of the efficiency of these algorithms is developed. The multilayer perceptron, the Volterra network and the cascade-correlation network are used as structures of artififfcial neural networks. Different methods of non-linear programming such as gradient and non-gradient methods are used for the calculation of the weight coefficients.
