| INFORMATION CODING AND NEURAL COMPUTING (2008) | |||||||||||||||
Abstract | |||||||||||||||
| Abstract. In [2,5] it is showed that programming languages can be translated into recurrent neural nets. Implementation of programming languages in neural nets turns to be not only theoretical exciting but has also some practical implications in the recent efforts to merge symbolic and subsymbolic computation. To be of some use it should be carried in the context of bounded resources. With the guidelines provided in [4,5], we introduce data types and show how to encode and keep them inside the information flow of neural nets. 1 | |||||||||||||||
Publication details | |||||||||||||||
| |||||||||||||||