Visualising large-scale neural network models in real-timeCitation formats

  • Authors:
  • Cameron Patterson
  • Francesco Galluppi
  • Alexander Rast
  • Steve Furber

Standard

Visualising large-scale neural network models in real-time. / Patterson, Cameron; Galluppi, Francesco; Rast, Alexander; Furber, Steve.

Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks. 2012.

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Harvard

Patterson, C, Galluppi, F, Rast, A & Furber, S 2012, Visualising large-scale neural network models in real-time. in Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks. 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012, Brisbane, QLD, 1/07/12. https://doi.org/10.1109/IJCNN.2012.6252490

APA

Patterson, C., Galluppi, F., Rast, A., & Furber, S. (2012). Visualising large-scale neural network models in real-time. In Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks https://doi.org/10.1109/IJCNN.2012.6252490

Vancouver

Patterson C, Galluppi F, Rast A, Furber S. Visualising large-scale neural network models in real-time. In Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks. 2012 https://doi.org/10.1109/IJCNN.2012.6252490

Author

Patterson, Cameron ; Galluppi, Francesco ; Rast, Alexander ; Furber, Steve. / Visualising large-scale neural network models in real-time. Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks. 2012.

Bibtex

@inproceedings{5ee8a8a5048a4efbb02d3efa48256572,
title = "Visualising large-scale neural network models in real-time",
abstract = "As models of neural networks scale in concert with increasing computational performance, gaining insight into their operation becomes increasingly important. This paper proposes an efficient and generalised method to access simulation data via in-system aggregation, providing visualised representation at all layers of the network in real-time. Enabling neural networks for real-time visualisation allows a user to gain insight into the network dynamics of their systems as they operate over time. This visibility also permits users (or a computational agent) to determine whether early intervention is required to adjust parameters, or even to terminate operation of experimental networks that are not operating correctly. Conventionally the determination of correctness would occur post-simulation, so with sufficient in-flight insight, a significant advantage may be obtained, and compute time minimised. For this paper we apply the real-time visualisation platform to the SpiNNaker programmable neuromimetic system and a variety of neural network models. The visualisation platform is shown to be capable across a range of diverse simulations, and at supporting differing layers of network abstraction, requiring minimal configuration to represent each model. The resulting general-purpose visualisation platform for neural networks, is effective at presenting data to users in order to aid their comprehension of the network dynamics during operation, and scales from small to biologically-significant network sizes. {\textcopyright} 2012 IEEE.",
keywords = "Biological system modeling , Brain models , Computational modeling , Data visualization , Neurons , Real time systems",
author = "Cameron Patterson and Francesco Galluppi and Alexander Rast and Steve Furber",
year = "2012",
doi = "10.1109/IJCNN.2012.6252490",
language = "English",
isbn = "9781467314909",
booktitle = "Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks",
note = "2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 ; Conference date: 01-07-2012",

}

RIS

TY - GEN

T1 - Visualising large-scale neural network models in real-time

AU - Patterson, Cameron

AU - Galluppi, Francesco

AU - Rast, Alexander

AU - Furber, Steve

PY - 2012

Y1 - 2012

N2 - As models of neural networks scale in concert with increasing computational performance, gaining insight into their operation becomes increasingly important. This paper proposes an efficient and generalised method to access simulation data via in-system aggregation, providing visualised representation at all layers of the network in real-time. Enabling neural networks for real-time visualisation allows a user to gain insight into the network dynamics of their systems as they operate over time. This visibility also permits users (or a computational agent) to determine whether early intervention is required to adjust parameters, or even to terminate operation of experimental networks that are not operating correctly. Conventionally the determination of correctness would occur post-simulation, so with sufficient in-flight insight, a significant advantage may be obtained, and compute time minimised. For this paper we apply the real-time visualisation platform to the SpiNNaker programmable neuromimetic system and a variety of neural network models. The visualisation platform is shown to be capable across a range of diverse simulations, and at supporting differing layers of network abstraction, requiring minimal configuration to represent each model. The resulting general-purpose visualisation platform for neural networks, is effective at presenting data to users in order to aid their comprehension of the network dynamics during operation, and scales from small to biologically-significant network sizes. © 2012 IEEE.

AB - As models of neural networks scale in concert with increasing computational performance, gaining insight into their operation becomes increasingly important. This paper proposes an efficient and generalised method to access simulation data via in-system aggregation, providing visualised representation at all layers of the network in real-time. Enabling neural networks for real-time visualisation allows a user to gain insight into the network dynamics of their systems as they operate over time. This visibility also permits users (or a computational agent) to determine whether early intervention is required to adjust parameters, or even to terminate operation of experimental networks that are not operating correctly. Conventionally the determination of correctness would occur post-simulation, so with sufficient in-flight insight, a significant advantage may be obtained, and compute time minimised. For this paper we apply the real-time visualisation platform to the SpiNNaker programmable neuromimetic system and a variety of neural network models. The visualisation platform is shown to be capable across a range of diverse simulations, and at supporting differing layers of network abstraction, requiring minimal configuration to represent each model. The resulting general-purpose visualisation platform for neural networks, is effective at presenting data to users in order to aid their comprehension of the network dynamics during operation, and scales from small to biologically-significant network sizes. © 2012 IEEE.

KW - Biological system modeling , Brain models , Computational modeling , Data visualization , Neurons , Real time systems

U2 - 10.1109/IJCNN.2012.6252490

DO - 10.1109/IJCNN.2012.6252490

M3 - Conference contribution

SN - 9781467314909

BT - Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks

T2 - 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012

Y2 - 1 July 2012

ER -