Neural programming language
Hava T. Siegelmann · National Conference on Artificial Intelligence · 1994
Analog recurrent neural networks have attracted much attention lately as powerful tools of automatic learning. We formally define a high level language, called NEural Langage, which is rich enough to express any computer algorithm or rule-based system. We show how to compile a NEL program to a network which computes exactly as the original program and requires the same computation time. We suggest this language along with its compiler as the ultimate bridge from symbolic to analog computation, and propose its outcome as an initial network for learning.
Cited by 15 works.
Authors
References
- Introduction to the theory of neural computation
- Forward Models: Supervised Learning with a Distal Teacher
- The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems
- Learning from hints in neural networks
- Learning, invariance, and generalization in high-order neural networks
- Refinement of approximate domain theories by knowledge-based neural networks
- Unified integration of explicit knowledge and learning by example in recurrent networks
- Symbolic-neural systems and the use of hints for developing complex systems
- On the Computational Power of Neural Nets
- Turing computability with neural nets