Evaluation of Adaptive Mixtures of Competing Experts

  title={Evaluation of Adaptive Mixtures of Competing Experts},
  author={Steven J. Nowlan and Geoffrey E. Hinton},
We compare the performance of the modular architecture, composed of competing expert networks, suggested by Jacobs, Jordan, Nowlan and Hinton (1991) to the performance of a single back-propagation network on a complex, but low-dimensional, vowel recognition task. Simulations reveal that this system is capable of uncovering interesting decompositions in a complex task. The type of decomposition is strongly influenced by the nature of the input to the gating network that decides which expert to… CONTINUE READING

From This Paper

Topics from this paper.


Publications citing this paper.
Showing 1-10 of 60 extracted citations


Publications referenced by this paper.
Showing 1-7 of 7 references

Soft Competitive Adaptation: Neural Network Learning Algorithms based on Fitting Statistical Mixtures

S. J. Nowlan
PhD thesis, • 1991
View 5 Excerpts
Highly Influenced

Classification of self-normalized vowels

L. J. Gerstman
IEEE Trans. on Audio and Electroacoustics, • 1968
View 1 Excerpt
Highly Influenced

Competing experts: An experimental investigation of asssociative mixture models

S. J. Nowlan
Technical Report CRG-TR-90-5, • 1990
View 2 Excerpts

Similar Papers

Loading similar papers…