JUCS - Journal of Universal Computer Science 7(11): 1006-1023, doi: 10.3217/jucs-007-11-1006
A Neural Abstract Machine
expand article infoEgon Börger, Diego Sona§
‡ University of Pisa, Pisa, Italy§ Dipartimento di Informatica, Università di Pisa, Pisa, Italy
Open Access
Abstract
In an attempt to capture the fundamental features that are common to neural networks, we define a parameterized Neural Abstract Machine (NAM) in such a way that the major neural networks in the literature can be described as natural extensions or refinements of the NAM. We illustrate the refinement for feedforward networks with back-propagation training. The NAM provides a platform and programming language independent basis for a comparative mathematical and experimental analysis and evaluation of different implementations of neural networks. We concentrate our attention here on the computational core (Neural Kernel NK) and provide abstract interfaces for the other NAM components.
Keywords
neural networks, neural abstract machine, abstract state machines, distributed computation