Content uploaded by Stephen L. Thaler
Author content
All content in this area was uploaded by Stephen L. Thaler on Nov 17, 2015
Content may be subject to copyright.
A preview of the PDF is not available
Integrated Substrate and Thin Film Design Methods
Abstract and Figures
An artificial neural network cascade, containing 16 individual network modules and approximately 1,000 processing units, has produced an interactive database of nearly a quarter million potential binary and ternary chemical systems. While many of these hypothetical materials are anticipated to be thermodynamically stable, they are most likely kinetically inaccessible via typical bulk chemistry routes. However, since modem thin film technology allows a wide range of exotic compositions and stoichiometries via deposition, surface treatments, and nano-fabrication, it is anticipated that this newly acquired theoretical database will form a comprehensive road map to the formation of previously unattainable materials that offer significant technological advantages. Further, with the suite of available coating materials greatly expanded, thin film designers now have at their disposal the means to implement multilayer and composite thin film device designs that fulfill a much broader range of performance requirements and that are ideally matched to both underlying substrate and external working environment.
Figures - uploaded by Stephen L. Thaler
Author content
All figure content in this area was uploaded by Stephen L. Thaler
Content may be subject to copyright.
ResearchGate has not been able to resolve any citations for this publication.
This abstract describes a novel and very expeditious application of auto-associative
feedforward neural networks and autonomous discovery to real-time model-based fault
detection and identification within ill-defined dynamic systems. The observation of
such systems or processes under stable conditions allows for the autonomous
generation of both a neural and a qualitative algebraic model. Predictions can then be
computed across the feedforward network and compared with subsequent
observations to detect parameter abnormalities. The algebraic relationship between
these isolated and suspect process variables is then analytically established.
Experimental results with both real and artificial data are given along with a detailed
sensitivity analysis.
When a user gradually relaxes or destroys the internal architecture of a trained neural network, the network tends to spontaneously produce a succession of 'impressions' from its learned knowledge domain. This produces a mixture of both straightforward and hybridized exemplars from its training set. If a second neural network is allowed to watch for useful concepts that emerge from the first, a Creativity Machine is formed. In most cases, machines of this type perform remarkable feats of invention and discovery.
Recent experiments have shown that a trained chaotic network supervised by an associative net may produce human level discovery and invention. Extending this so-called “Creativity Machine Paradigm” to more complex cascades of chaotic networks not only allows for more ambitious forms of discovery such as juxtapositional invention, but also suggests a nomenclature and a convenient classification scheme for creative human achievements.