Hybrid Feedforward Neural Networks for Solving Classification Problems

@article{Ciocoiu2002HybridFN,
  title={Hybrid Feedforward Neural Networks for Solving Classification Problems},
  author={Iulian B. Ciocoiu},
  journal={Neural Processing Letters},
  year={2002},
  volume={16},
  pages={81-91}
}
A novel multistage feedforward network is proposed for efficient solving of difficult classification tasks. The standard Radial Basis Functions (RBF) architecture is modified in order to alleviate two potential drawbacks, namely the ‘curse of dimensionality’ and the limited discriminatory capacity of the linear output layer. The first goal is accomplished by feeding the hidden layer output to the input of a module performing Principal Component Analysis (PCA). The second one is met by… CONTINUE READING
8 Citations
16 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-8 of 8 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 16 references

Adaptive radial basis function nonlinearities and the problem of generalization

  • D. Lowe
  • Proceedings IEE Conference on ANN,
  • 1989
Highly Influential
3 Excerpts

Neural Networks for Pattern Recognition

  • C. M. Bishop
  • 1995
2 Excerpts

Application of an Architecturally Dynamic Network for Speech Pattern Classification

  • V. Kadirkamanathan, M. Niranjan
  • Proceedings Inst. Acoustics,
  • 1992

Similar Papers

Loading similar papers…