Automated Data Acquisition for In-Situ Material-Processing Modeling

Exploiting the many analogies between biological neurons and the cells within a spreadsheet application, we have succeeded in constructing independtly functioning, self-trained neural network cascades that are capable of (1) forming models of their spreadsheet environment, (2) manipulating data, (3) identifying anomalous information or noise, (4) locomotion, and (5) control over external instruments or devices. If information gathered by process sensors is fed through a spreadsheet application by dynamic data exchange, such neurological cascades or "databots" may be used to patrol the resulting databases, automatically identifying systematic and random noise, forming both neural and semantic models, organizing data, and coordinating external sensors and actuators. These accomplishments are made possible through two pioneering efforts. The first is the so-called "Creativity Machine Paradigm," allow autonomous discovery and planning using a tandem arrangement of chaotic and supervising networks. The second achievement involves the implementation of this paradigm without the use of any algorithmic code, instead using the inherent parallel processing capacity built into spreadsheet applications via cell referencing and resident spreadsheet functions. Autonomy of this spreadsheet "organism" is guaranteed by the encapsulation of both data and function, reminiscent of object-oriented programming, but now implemented in a virtual, analog network.