C. J. Kennedy (2000). Strongly Typed Evolutionary Programming. PhD Thesis, University of Bristol, Department of Computer Science. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
The Use of Functional and Logic Languages in Machine Learning - Flach (2000) (Correct)
....be a list of tuples) Higher order representations generalise this further by allowing sets and multisets. 4 Further examples illustrating the Escher representation can be found in [8] A higherorder decision tree learner is described in [1] and a higher order evolutionary progamming system in [15]. 4 Concluding remarks This paper has provided an introduction to ILP for non machine learners. We have also given an example of a learning problem represented in Escher. In the talk I will outline the specific advantages of using a language like Escher for learning. Acknowledgements This work ....
C.J. Kennedy. Strongly typed evolutionary programming. PhD Thesis, University of Bristol, 2000.
A Higher-order Approach to Meta-learning - Bensusan, Giraud-Carrier, Kennedy (2000) (2 citations) Self-citation (Kennedy) (Correct)
....the complex structures captured by the above representation. A discussion of these algorithms is beyond the scope of this paper. For details, we refer the reader to [5,6] for the description of a decision tree learner, to [13] for the description of a sequential covering algorithm and to [9, 10] for the description of an evolutionary system. 3 Meta learning from Induced Decision Trees The experiments described in [2, 3] were the first ones to make use of information computed from induced decision trees to characterise tasks in meta learning. Before showing our approach to automating ....
....represented by induced decision trees. We have briefly described a framework in which such a representation is possible and speculated on the kind of meta knowledge one might expect from this. Experiments must now be set up to validate the idea. We are currently extending the system described in [10] to carry out experiments. Our motivation for using the trees directly is that the predefined properties used in decision tree based characterisation (see subsection 3.1) only make explicit properties implicit in the tree structure. In addition, these properties have to be calculated a priori ....
C. J. Kennedy (2000). Strongly Typed Evolutionary Programming. PhD Thesis, University of Bristol, Department of Computer Science.
A Higher-order Approach to Meta-learning - Bensusan, Giraud-Carrier, Kennedy (2000) (2 citations) Self-citation (Kennedy) (Correct)
....the complex structures captured by the above representation. A discussion of these algorithms is beyond the scope of this paper. For details, we refer the reader to [4, 5] for the description of a decision tree learner, to [12] for the description of a sequential covering algorithm and to [8, 9] for the description of an evolutionary system. 4 Bensusan et al. 3 Meta learning from Induced Decision Trees The experiments described in [1, 2] were the first ones to make use of information computed from induced decision trees to characterise tasks in meta learning. Before showing our ....
....represented by induced decision trees. We have briefly described a framework in which such a representation is possible and speculated on the kind of meta knowledge one might expect from this. Experiments must now be set up to validate the idea. We are currently extending the system described in [9] to carry out experiments. Our motivation for using the trees directly is that the predefined properties used in decision tree based characterisation (see subsection 3.1) only make explicit properties implicit in the tree structure. In addition, these properties have to be calculated a priori ....
C. J. Kennedy (2000). Strongly Typed Evolutionary Programming. PhD Thesis, University of Bristol, Department of Computer Science.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC