Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
405639 | Neural Networks | 2008 | 8 Pages |
This paper presents new experimental results on the variadic neural network (VNN) [McGregor, S. (2007). Neural network processing for multiset data. In Proceedings: Vol. 4668. Artificial neural networks — ICANN 2007, 17th international conference (pp. 460–470). Springer]. The inputs to a variadic network are an arbitrary-length list of nn-tuples of real numbers, where nn is fixed, and the function computed by the network is unaffected by permutation of the inputs. This paper describes improvements in the training algorithm for the variadic perceptron, based on a constructive cascade topology, and performance of the improved networks on geometric problems inspired by vector graphics. Further development may allow practical application of these or similar networks to vector graphics processing and statistical analysis.