Skip to main content

Active Foreground Neural Network

Part of the Lecture Notes in Electrical Engineering book series (LNEE,volume 553)

Abstract

Active Foreground Neural Network (AFNN) is a revolutionary neural network which aims at bridging the computation, learning, and application’s implementation gap across conventional neural networks and cognitive learning processes with dual-band training and application layers. The aim is to perform asynchronous and parallel training of cross-interface Artificial Intelligence models with simultaneous implementation of the same. Therefore, the user may or may not need to implement the learning model.

Keywords

  • Active Foreground Neural Network (AFNN)
  • Artificial neural network (ANN)
  • Tensor processing unit (TPU)
  • OpenCL (Open Computation Library)
  • Compute Unified Device Architecture (CUDA)
  • Graphical processing unit (GPU)

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-981-13-6772-4_45
  • Chapter length: 9 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   169.00
Price excludes VAT (USA)
  • ISBN: 978-981-13-6772-4
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   219.99
Price excludes VAT (USA)
Hardcover Book
USD   279.99
Price excludes VAT (USA)
Fig. 1
Fig. 2
Fig. 3

References

  1. Butler S (1863 June 13) Darwin among the machines. Letters to the editor. The Press. Christchurch, New Zealand. Retrieved 16 October 2014, via Victoria University of Wellington

    Google Scholar 

  2. Hochreiter S (1991) Untersuchungen zu dynamischen neuronalen Netzen. Diploma thesis. Institut f. Informatik, Technische Univ. Munich. Advisor: J. Schmidhuber

    Google Scholar 

  3. Hochreiter S et al (2001 Jan 15) Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In: Kolen JF, Kremer SC (eds) A field guide to dynamical recurrent networks. Wiley, New York. ISBN 978-0-7803-5369-5

    Google Scholar 

  4. McCulloch W, Walter P (1943) A logical calculus of ideas immanent in nervous activity. Bull Math Biophys

    Google Scholar 

  5. Werbos PJ (1975) Beyond regression: new tools for prediction and analysis in the behavioral sciences

    Google Scholar 

  6. Jouppi N (2016 May 18) Google supercharges machine learning tasks with TPU custom chip. Google Cloud Platform Blog. Google

    Google Scholar 

  7. Christopher H, Paul W (2010 Dec 21) Social engineering. Wiley, New York. ISBN 978-0-470-63953-5

    Google Scholar 

  8. ACM (1998) ACM computing classification system: artificial intelligence. Retrieved 30 Aug 2007

    Google Scholar 

  9. Serenko A (2010) The development of an AI journal ranking based on the revealed preference approach (PDF). J Informetr 4(4):447–459

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ayush Aggarwal .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2019 Springer Nature Singapore Pte Ltd.

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Aggarwal, A., Gupta, S.C. (2019). Active Foreground Neural Network. In: Mishra, S., Sood, Y., Tomar, A. (eds) Applications of Computing, Automation and Wireless Systems in Electrical Engineering. Lecture Notes in Electrical Engineering, vol 553. Springer, Singapore. https://doi.org/10.1007/978-981-13-6772-4_45

Download citation

  • DOI: https://doi.org/10.1007/978-981-13-6772-4_45

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-13-6771-7

  • Online ISBN: 978-981-13-6772-4

  • eBook Packages: EngineeringEngineering (R0)