Sökning: "Neural networks"

Visar resultat 26 - 30 av 496 avhandlingar innehållade orden Neural networks.

1. 26. Discrete-Time Cellular Neural Networks Implemented on Field-Programmable Gate-Arrays to Build a Virtual Sensor System

   Författare :Suleyman Malki; Institutionen för elektro- och informationsteknik; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Cellular Neural Networks; Image processing; Discrete-Time Cellular Neural Networks; Packet switching; FPGA; Velocity measurement; Autowaves; Robot navigation;

   Sammanfattning : Image processing is one of the popular applications of Cellular Neural Networks. Macro enriched field-programmable gate-arrays can be used to realize such systems on silicon. At first glance a pipelined approach, based on circuit switching, seems promising. LÄS MER

3. 27. Towards a framework for reinforcement learning with artificial neural networks

   Författare :Peter Raicevic; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; aritficial neural networks; reinforcement learning; BCPNN; modularity; genetic algorithms; Computer science; Datavetenskap;

   Sammanfattning : .... LÄS MER

4. 28. On Hardware Implementation of Discrete-Time Cellular Neural Networks

   Författare :Suleyman Malki; Institutionen för elektro- och informationsteknik; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Circuit switching; Network on Chip; Vein feature extraction; Velocity measurement; Discrete-Time Cellular Neural Network; Switched broadcast; Serialized broadcast; Cellular Neural Network; Field- Programmable Gate-Array; Image processing.;

   Sammanfattning : Cellular Neural Networks are characterized by simplicity of operation. The network consists of a large number of nonlinear processing units; called cells; that are equally spread in the space. LÄS MER

5. 29. On Improving Validity of Deep Neural Networks in Safety Critical Applications

   Författare :Jens Henriksson; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; out-of-distribution; outlier detection; deep neural networks; Safety critical applications;

   Sammanfattning : Context: Deep learning has proven to be a valuable component in object detection and classification, as the technique has shown an increased performance throughput compared to traditional software algorithms. Deep learning refers to the process, in which an optimisation process learns an algorithm through a set of labeled data, where the researcher defines an architecture rather than the algorithm itself. LÄS MER

7. 30. Sequence learning in the Bayesian Confidence Propagation Neural Network

   Författare :Ramon Heberto Martinez Mayorquin; Pawel Herman; Anders Lansner; Matthias Hennig; Thomas Wennekers; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; bayesian; learning; neural networks; sequences; Computer Science; Datalogi;

   Sammanfattning : This thesis examines sequence learning in the Bayesian Confidence PropagationNeural Network (BCPNN). The methodology utilized throughout this work is com-putational and analytical in nature and the contributions here presented can beunderstood along the following four major themes: 1) this work starts by revisitingthe properties of the BCPNN as an attractor neural network and then provides anovel formalization of some of those properties. LÄS MER