Sciweavers

762 search results - page 6 / 153
» Constructive Neural Network Learning Algorithms
Sort
View
VIP
2003
13 years 9 months ago
Edge Detection Based on Modified BP Algorithm of ANN
1 Accurately locating edge points is important for image measurement. This paper describes an edge detection method based on back-propagation algorithm of neural networks. A three-...
Lihong Zheng, Xiangjian He
IJON
1998
119views more  IJON 1998»
13 years 7 months ago
Comment on "Recurrent neural networks: A constructive algorithm, and its properties"
In their paper [1], Tsoi and Tan present what they call a "canonical form", which they claim to be identical to that proposed in Nerrand et al [2]. They also claim that ...
Léon Personnaz, Gérard Dreyfus
ICANN
2007
Springer
13 years 11 months ago
Active Learning to Support the Generation of Meta-examples
Meta-Learning has been used to select algorithms based on the features of the problems being tackled. Each training example in this context, i.e. each meta-example, stores the feat...
Ricardo Bastos Cavalcante Prudêncio, Teresa ...
PPSN
1990
Springer
13 years 11 months ago
Feature Construction for Back-Propagation
T h e ease of learning concepts f r o m examples in empirical machine learning depends on the attributes used for describing the training d a t a . We show t h a t decision-tree b...
Selwyn Piramuthu
CORR
2010
Springer
150views Education» more  CORR 2010»
13 years 7 months ago
Extraction of Symbolic Rules from Artificial Neural Networks
Although backpropagation ANNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions c...
S. M. Kamruzzaman, Md. Monirul Islam