The cascade-correlation learning architecture
Advances in neural information processing systems 2
Solving the multiple instance problem with axis-parallel rectangles
Artificial Intelligence
Involving Aggregate Functions in Multi-relational Search
PKDD '02 Proceedings of the 6th European Conference on Principles of Data Mining and Knowledge Discovery
Transformation-Based Learning Using Multirelational Aggregation
ILP '01 Proceedings of the 11th International Conference on Inductive Logic Programming
Learning Aggregate Functions with Neural Networks Using a Cascade-Correlation Approach
ILP '08 Proceedings of the 18th international conference on Inductive Logic Programming
Refining aggregate conditions in relational learning
PKDD'06 Proceedings of the 10th European conference on Principle and Practice of Knowledge Discovery in Databases
Classifying relational data with neural networks
ILP'05 Proceedings of the 15th international conference on Inductive Logic Programming
Trust alignment: a sine qua non of open multi-agent systems
OTM'11 Proceedings of the 2011th Confederated international conference on On the move to meaningful internet systems - Volume Part I
Engineering trust alignment: Theory, method and experimentation
International Journal of Human-Computer Studies
| Hi-index | 0.00 |
In various application domains, data can be represented as bags of vectors instead of single vectors. Learning aggregate functions from such bags is a challenging problem. In this paper, a number of simple neural network approaches and a combined approach based on cascade-correlation are examined in order to handle this kind of data. Adapted feedforward networks, recurrent networks and networks with special aggregation units integrated in the network can all be used to construct networks that are capable of learning aggregate function. A combination of these three approaches is possible by using cascade-correlation, creating a method that automatically chooses the best of these options. Results on artificial and multi-instance data sets are reported, allowing a comparison between the different approaches.