Wrning, Hardcore post here: I would not bet on it but there is now a connection between XML and neural network. For people not confortable with neural network, it's an artificial intelligence technique that aim to simulate some properties of real neural networks in order to do cognitive modeling (which actually works pretty well for pattern recognition and classification tasks). XML is data formalism. Now let's turn to this: XML-BASED FORMAT FOR TRAINED NEURAL NETWORK DEFINITION by D.V. Rubtsov, S.V. Butakov.

In this work a format for neural network models description is introduced. Its main purpose is to provide a unified way for neural network model definition. Format allows interchanging neural models as well as documentation, store and manipulating them independently from the simulation system that produced it. We propose to use XML notation for full description of neural models, including data dictionary, properties of training sample, preprocessing methods, details of network structure and parameters, method for network output interpretation. The first version of DTD for neural model description language is developed. A model description structure, contents of main issues in XML document and example of software structure for handling files with neural model description are presented.

Roughly speaking, here is a concrete example (it might be not so concrete for those not aware with both concepts): The scary image on the left is described by the XML format and turned into another scary image on the right. Why do I blog this? because this providing a unified description of a neural network is a vers relevant idea. I am interested by this because I do think it's relevant for cognitive science research. Besides, the use of the XML technology (a web tech!) is an intriguing by-product of this project: the underlying presence of the Internet/Web: it's implicitly present in the project: the Internet takes a central part here (which is not obvious with regard to the neural network definition).