| DC Field | Value | Language |
|---|
| dc.contributor.author | Kharchenko, Kostyantyn | |
| dc.contributor.author | Beznosyk, Oleksandr | |
| dc.contributor.author | Romanov, Valeriy | |
| dc.coverage.temporal | 21-25 August 2018, Lviv | |
| dc.date.accessioned | 2020-06-19T12:05:53Z | - |
| dc.date.available | 2020-06-19T12:05:53Z | - |
| dc.date.created | 2018-02-28 | |
| dc.date.issued | 2018-02-28 | |
| dc.identifier.citation | Kharchenko K. Implementation of Neural Networks with Help of a Data Flow Virtual Machine / Kostyantyn Kharchenko, Oleksandr Beznosyk, Valeriy Romanov // Data stream mining and processing : proceedings of the IEEE second international conference, 21-25 August 2018, Lviv. — Львів : Lviv Politechnic Publishing House, 2018. — P. 407–410. — (Hybrid Systems of Computational Intelligence). | |
| dc.identifier.isbn | © Національний університет „Львівська політехніка“, 2018 | |
| dc.identifier.isbn | © Національний університет „Львівська політехніка“, 2018 | |
| dc.identifier.uri | https://ena.lpnu.ua/handle/ntb/52534 | - |
| dc.description.abstract | The main goal of this paper is to show how a
neural network can be implemented with help of the data flow
management system at a virtual machine. As an example, the
three-layer neural network realization has been investigated to
solve a simple XOR function with two inputs and one output.
For that purpose, a sigmoid command required to make a
neuron activation function has been added into the data flow
virtual machine. It is presented in the paper that neural
networks can be described as data flows with help of the
declarative approach on a base of the JSON format. | |
| dc.format.extent | 407-410 | |
| dc.language.iso | en | |
| dc.publisher | Lviv Politechnic Publishing House | |
| dc.relation.ispartof | Data stream mining and processing : proceedings of the IEEE second international conference, 2018 | |
| dc.relation.uri | http://download.tensorflow.org/paper/whitepaper2015.pdf | |
| dc.relation.uri | https://github.com/Theano | |
| dc.relation.uri | https://mxnet.apache.org/ | |
| dc.relation.uri | https://www.microsoft.com/en-us/cognitive-toolkit/ | |
| dc.relation.uri | https://keras.io/ | |
| dc.relation.uri | https://github.com/torch/torch7 | |
| dc.relation.uri | http://torch.ch/ | |
| dc.relation.uri | http://caffe.berkeleyvision.org/ | |
| dc.subject | neural networks | |
| dc.subject | data flow virtual machine | |
| dc.subject | JSON | |
| dc.subject | activation functions | |
| dc.title | Implementation of Neural Networks with Help of a Data Flow Virtual Machine | |
| dc.type | Conference Abstract | |
| dc.rights.holder | © Національний університет “Львівська політехніка”, 2018 | |
| dc.contributor.affiliation | National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” | |
| dc.format.pages | 4 | |
| dc.identifier.citationen | Kharchenko K. Implementation of Neural Networks with Help of a Data Flow Virtual Machine / Kostyantyn Kharchenko, Oleksandr Beznosyk, Valeriy Romanov // Data stream mining and processing : proceedings of the IEEE second international conference, 21-25 August 2018, Lviv. — Lviv Politechnic Publishing House, 2018. — P. 407–410. — (Hybrid Systems of Computational Intelligence). | |
| dc.relation.references | [1] K. V. Kharchenko, “Extension of the LLVM virtual machine with parallel instructions to implement a message transfer system,” 2012 System analysis and information technology 14th Int. Conf., Kyiv, Ukraine, p. 302, 24 April 2012. | |
| dc.relation.references | [2] K. V. Kharchenko, “Dataflow control paradigm and dataflow graphic presentation in SOA,” East-European journal for advanced technologies, no. 3/9 (69), pp. 22-29, 2014. | |
| dc.relation.references | [3] K. V. Kharchenko, “An Architecture and Test Implementation of Data Flow Virtual Machine,” 2016 System analysis and information technology 18th Int. Conf., Kyiv, Ukraine, p. 268, 30 May – 2 June 2016. | |
| dc.relation.references | [4] K. Kharchenko, O. Beznosyk and V. Romanov, “A Set of Instructions for Data Flow Virtual Machine,” IEEE First Ukraine Conference on Electrical and Computer Engineering (UKRCON 2017), Kyiv, Ukraine, pp. 931-934, 29 May – 2 June 2017. | |
| dc.relation.references | [5] B. Lu, B. L. Evans and D. V. Tosic, "Simulation and Synthesis of Artificial Neural Networks Using Dataflow Models in Ptolemy," 4th Seminar on Neural Network Applications in Electrical Engineering NEUREL-97, Belgrade, Serbia, pp. 84-89, Sep. 8-9, 1997. | |
| dc.relation.references | [6] M. Bacis, G. Natale, E. Del Sozzo and M. D. Santambrogio, “A pipelined and scalable dataflow implementation of convolutional neural networks on FPGA,” 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), Lake Buena Vista, FL, pp. 90-97, 2017. | |
| dc.relation.references | [7] Y. H. Chen, J. Emer and V. Sze, "Using Dataflow to Optimize Energy Efficiency of Deep Neural Network Accelerators," in IEEE Micro, vol. 37, no. 3, pp. 12-21, 2017. | |
| dc.relation.references | [8] Jeffrey Dean et al. (2015, November 9). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems [Online]. Available: http://download.tensorflow.org/paper/whitepaper2015.pdf | |
| dc.relation.references | [9] Theano GitHub [Online]. Available: https://github.com/Theano | |
| dc.relation.references | [10] MXNet: A Scalable Deep Learning Framework [Online]. Available: https://mxnet.apache.org/ | |
| dc.relation.references | [11] Microsoft Cognitive Toolkit [Online]. Available: https://www.microsoft.com/en-us/cognitive-toolkit/ | |
| dc.relation.references | [12] Keras Documentation [Online]. Available: https://keras.io/ | |
| dc.relation.references | [13] Torch GitHub [Online]. Available: https://github.com/torch/torch7 | |
| dc.relation.references | [14] Torch. Scientific computing for LuaJIT [Online]. Available: http://torch.ch/ | |
| dc.relation.references | [15] Caffee Deep Learning Framework [Online]. Available: http://caffe.berkeleyvision.org/ | |
| dc.relation.referencesen | [1] K. V. Kharchenko, "Extension of the LLVM virtual machine with parallel instructions to implement a message transfer system," 2012 System analysis and information technology 14th Int. Conf., Kyiv, Ukraine, p. 302, 24 April 2012. | |
| dc.relation.referencesen | [2] K. V. Kharchenko, "Dataflow control paradigm and dataflow graphic presentation in SOA," East-European journal for advanced technologies, no. 3/9 (69), pp. 22-29, 2014. | |
| dc.relation.referencesen | [3] K. V. Kharchenko, "An Architecture and Test Implementation of Data Flow Virtual Machine," 2016 System analysis and information technology 18th Int. Conf., Kyiv, Ukraine, p. 268, 30 May – 2 June 2016. | |
| dc.relation.referencesen | [4] K. Kharchenko, O. Beznosyk and V. Romanov, "A Set of Instructions for Data Flow Virtual Machine," IEEE First Ukraine Conference on Electrical and Computer Engineering (UKRCON 2017), Kyiv, Ukraine, pp. 931-934, 29 May – 2 June 2017. | |
| dc.relation.referencesen | [5] B. Lu, B. L. Evans and D. V. Tosic, "Simulation and Synthesis of Artificial Neural Networks Using Dataflow Models in Ptolemy," 4th Seminar on Neural Network Applications in Electrical Engineering NEUREL-97, Belgrade, Serbia, pp. 84-89, Sep. 8-9, 1997. | |
| dc.relation.referencesen | [6] M. Bacis, G. Natale, E. Del Sozzo and M. D. Santambrogio, "A pipelined and scalable dataflow implementation of convolutional neural networks on FPGA," 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), Lake Buena Vista, FL, pp. 90-97, 2017. | |
| dc.relation.referencesen | [7] Y. H. Chen, J. Emer and V. Sze, "Using Dataflow to Optimize Energy Efficiency of Deep Neural Network Accelerators," in IEEE Micro, vol. 37, no. 3, pp. 12-21, 2017. | |
| dc.relation.referencesen | [8] Jeffrey Dean et al. (2015, November 9). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems [Online]. Available: http://download.tensorflow.org/paper/whitepaper2015.pdf | |
| dc.relation.referencesen | [9] Theano GitHub [Online]. Available: https://github.com/Theano | |
| dc.relation.referencesen | [10] MXNet: A Scalable Deep Learning Framework [Online]. Available: https://mxnet.apache.org/ | |
| dc.relation.referencesen | [11] Microsoft Cognitive Toolkit [Online]. Available: https://www.microsoft.com/en-us/cognitive-toolkit/ | |
| dc.relation.referencesen | [12] Keras Documentation [Online]. Available: https://keras.io/ | |
| dc.relation.referencesen | [13] Torch GitHub [Online]. Available: https://github.com/torch/torch7 | |
| dc.relation.referencesen | [14] Torch. Scientific computing for LuaJIT [Online]. Available: http://torch.ch/ | |
| dc.relation.referencesen | [15] Caffee Deep Learning Framework [Online]. Available: http://caffe.berkeleyvision.org/ | |
| dc.citation.conference | IEEE second international conference "Data stream mining and processing" | |
| dc.citation.spage | 407 | |
| dc.citation.epage | 410 | |
| dc.coverage.placename | Львів | |
| Appears in Collections: | Data stream mining and processing : proceedings of the IEEE second international conference
|
