Superior training of artificial neural networks using weight-space partitioning

2002 ◽  
Author(s):  
H.V. Gupta ◽  
Kuo-lin Hsu ◽  
S. Sorooshian
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Weight Space ◽  
Space Partitioning ◽  
Artificial Neural

scholarly journals The need for stochastic replication of ecological neural networks

2007 ◽  
Vol 362 (1479) ◽  
pp. 455-460 ◽  
Author(s):  
Colin R Tosh ◽  
Graeme D Ruxton
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Evolutionary Ecology ◽  
Training Data ◽  
Weight Space ◽  
Stochastic Variation ◽  
Feed Forward Network ◽  
Sample Error ◽  
Artificial Neural ◽  
Error Weight

Artificial neural networks are becoming increasingly popular as predictive statistical tools in ecosystem ecology and as models of signal processing in behavioural and evolutionary ecology. We demonstrate here that a commonly used network in ecology, the three-layer feed-forward network, trained with the backpropagation algorithm, can be extremely sensitive to the stochastic variation in training data that results from random sampling of the same underlying statistical distribution, with networks converging to several distinct predictive states. Using a random walk procedure to sample error–weight space, and Sammon dimensional reduction of weight arrays, we demonstrate that these different predictive states are not artefactual, due to local minima, but lie at the base of major error troughs in the error–weight surface. We further demonstrate that various gross weight compositions can produce the same predictive state, suggesting the analogy of weight space as a ‘patchwork’ of multiple predictive states. Our results argue for increased inclusion of stochastic training replication and analysis into ecological and behavioural applications of artificial neural networks.

FUTURE OF ARTIFICIAL NEURAL NETWORKS IN SPACE EXPLORATION AND SPACE ENGINEERING

2018 ◽  
pp. 6-11
Author(s):  
Kobiljon Kh. Zoidov ◽  
◽  
Svetlana V. Ponomareva ◽  
Daniel I. Serebryansky ◽  
◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Space Exploration ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document