A neuron model with trainable activation function (TAF) and its MFNN supervised learning

@article{Wu2001ANM,
  title={A neuron model with trainable activation function (TAF) and its MFNN supervised learning},
  author={Youshou Wu and Mingsheng Zhao},
  journal={Science in China Series : Information Sciences},
  year={2001},
  volume={44},
  pages={366-375}
}
This paper addresses a new kind of neuron model, which has trainable activation function (TAF) in addition to only trainable weights in the conventional M-P model. The final neuron activation function can be derived from a primitive neuron activation function by training. The BP like learning algorithm has been presented for MFNN constructed by neurons of TAF model. Several simulation examples are given to show the network capacity and performance advantages of the new MFNN in comparison with… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-2 OF 2 REFERENCES

A new perceptmn model with tunable activation function

  • Y. S. Wu, M. S. Zhao, X. Q. Ding
  • Science in China , Ser . E .
  • 1997

Similar Papers

Loading similar papers…