Creativity of Neural Networks
In the paper the ability of neural networks in creativity is tested. The creation of new words was chosen as an example task of creativity. Three different approaches based on the neural networks were designed and implemented to perform experiments. From all concerned solutions the best results was produced by the recurrent neural network.
KeywordsNeural Network Hide Layer Associative Memory Recurrent Neural Network Multilayered Perceptron
Unable to display preview. Download preview PDF.
- 1.Howard, G.: Frames of Mind. In: Basic Books (1983)Google Scholar
- 2.Chen, C.C.J.: Creating melodies with evolving recurrent neural networks. In: Proceedings of the 2001 International Joint Conference on Neural Networks (2001)Google Scholar
- 3.Westermann, G.: A constructivist neural network learns the past tense of english. In: Proceedings of the GALA 1997 Conference on Language Acquisition, pp. 393–398 (1997)Google Scholar
- 4.Thaler, S.: Autonomous ultrahard materials discovery via spreadsheet-implemented neural network cascades. JOM 49 (1997)Google Scholar
- 5.Levis, J.P.: Shape and texture generation by neural network creation paradigm. In: Computer Graphics Laboratory, http://www.idiom.com/~zilla/Work/texcbrfinal
- 7.Hertz, J., Krogh, A., Palmer, R.: Introduction to the theory of neural computation. Addison Wesley Publishing Company, Reading (1991)Google Scholar