Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Genetic programming: on the programming of computers by means of natural selection
Genetic programming: on the programming of computers by means of natural selection
Genetic programming II: automatic discovery of reusable programs
Genetic programming II: automatic discovery of reusable programs
Advances in genetic programming
Genetic programming: an introduction: on the automatic evolution of computer programs and its applications
Target detection in SAR imagery by genetic programming
Advances in Engineering Software
Genetic Programming for Feature Discovery and Image Discrimination
Proceedings of the 5th International Conference on Genetic Algorithms
Genetic Programming for Multiple Class Object Detection
AI '99 Proceedings of the 12th Australian Joint Conference on Artificial Intelligence: Advanced Topics in Artificial Intelligence
A domain-independentwindow approach to multiclass object detection using genetic programming
EURASIP Journal on Applied Signal Processing
An analysis of diversity of constants of genetic programming
EuroGP'03 Proceedings of the 6th European conference on Genetic programming
Morphological algorithm design for binary images using genetic programming
Genetic Programming and Evolvable Machines
| Hi-index | 0.00 |
This paper describes an approach to the use of gradient descent search in tree based genetic programming for object recognition problems. A weight parameter is introduced to each link between two nodes in a program tree. The weight is defined as a floating point number and determines the degree of contribution of the sub-program tree under the link with the weight. Changing a weight corresponds to changing the effect of the sub-program tree. The weight changes are learnt by gradient descent search at a particular generation. The programs are evolved and learned by both the genetic beam search and the gradient descent search. This approach is examined and compared with the basic genetic programming approach without gradient descent on three object classification problems of varying difficulty. The results suggest that the new approach works well on these problems.