Paper Search Console

Home Search Page About Contact

Journal Title

Title of Journal: Int J Mach Learn Cyber

Search In Journal Title:

Abbravation: International Journal of Machine Learning and Cybernetics

Search In Journal Abbravation:

Publisher

Springer Berlin Heidelberg

Search In Publisher:

DOI

10.1016/0022-1759(86)90337-6

Search In DOI:

ISSN

1868-808X

Search In ISSN:
Search In Title Of Papers:

Bifiring deep neural networks

Authors: JinCheng Li Wing W Y Ng Daniel S Yeung Patrick P K Chan
Publish Date: 2013/09/26
Volume: 5, Issue: 1, Pages: 73-83
PDF Link

Abstract

Deep neural networks provide more expressive power in comparison to shallow ones However current activation functions can not propagate error using gradient descent efficiently with the increment of the number of hidden layers Current activation functions eg sigmoid have large saturation regions which are insensitive to changes of hidden neuron’s input and yield gradient diffusion To relief these problems we propose a bifiring activation function in this work The bifiring function is a differentiable function with a very small saturation region Experimental results show that deep neural networks with the proposed activation functions yield faster training better error propagation and better testing accuracies on seven image datasets

Keywords:

References

.
Search In Abstract Of Papers:
Other Papers In This Journal:
  1. Bayesian networks for incomplete data analysis in form processing
  2. Concept lattice compression in incomplete contexts based on K -medoids clustering
  3. An auto-adaptive convex map generating path-finding algorithm: Genetic Convex A *
  4. Background subtraction based on modified online robust principal component analysis
  5. From Gaussian kernel density estimation to kernel methods
  6. Parameter selection algorithm with self adaptive growing neural network classifier for diagnosis issues
  7. State estimation for uncertain discrete-time stochastic neural networks with Markovian jump parameters and time-varying delays
  8. Cognitive concept learning from incomplete information
  9. Separating theorem of samples in Banach space for support vector machine learning
  10. Density peaks clustering using geodesic distances
  11. Resource-constrained project scheduling problem with uncertain durations and renewable resources
  12. Two swarm intelligence approaches for tuning extreme learning machine
  13. Switching control design based on state feedback for unstable plants
Search Result: