• Home
  • Stephen L. Thaler
Stephen L. Thaler

Stephen L. Thaler
Imagination Engines, Inc.

Ph.D., Physics

About

87
Publications
10,761
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
277
Citations
Introduction
Thaler is a scientist/inventor with over 20 years immersion in aerospace, therein working diverse areas including radiation effects in solids, high-energy lasers, low-observables technology, and the growth of exotic materials such as diamond within laser plasmas. He has nearly 40 years of experience in connectionism, with an intense interest in constraint softening in artificial neural networks to create new concepts and/or action plans. Currently he devotes most of his research to computational psychology using his patented artificial neural network paradigms.
Additional affiliations
May 1995 - present
Imagination Engines, Inc.
Position
  • President & CEO
Description
  • inventive neural architectures, patenting, government & commercial contracting/consulting
May 1995 - January 2016
Imagination Engines, Inc.
Position
  • President & CEO
Description
  • inventive neural architectures, patenting, government & commercial contracting/consulting
January 1991 - May 1995
McDonnell Douglas Aircraft Company
Position
  • Principal Technical Specialist
Description
  • non-destructive testing of airframe structures, the use of high energy laser plasmas for the growth of ultra-hard materials, and neural network modeling of airframe fatigue

Publications

Publications (87)
Patent
A container (10) for use, for example, for beverages, has a wall (12) with and external surface (14) and an internal wall (16) of substantially uniform thickness. The wall (12) has a fractal profile which provides a series of fractal elements (18-28) on the interior and exterior surfaces (14-16), forming pits (40) and bulges (42) in the profile of...
Patent
Devices for attracting enhanced attention include: an input signal of a lacunar pulse train having characteristics of a pulse frequency of approximately four Hertz and a pulse-train fractal dimension of approximately one- half; and at least one controllable light source configured to be pulsatingly operated by the input signal; wherein a neural fla...
Article
A novel form of neurocomputing allows machines to generate new concepts along with their anticipated consequences, all encoded as chained associative memories. Knowledge is accumulated by the system through direct experience as network chaining topologies form in response to various environmental input patterns. Thereafter, random disturbances to t...
Article
Full-text available
Prostate cancer is the second leading cause of cancer death in men in the developed world. A more sensitive and specific detection strategy for lethal prostate cancer beyond serum prostate specific antigen (PSA) population screening is urgently needed. Diagnosis by canine olfaction, using dogs trained to detect cancer by smell, has been shown to be...
Preprint
Full-text available
Prostate cancer is the second leading cause of cancer death in men in the developed world. A more sensitive and specific detection strategy for lethal prostate cancer beyond serum prostate specific antigen (PSA) population screening is urgently needed. Diagnosis by canine olfaction, using dogs trained to detect cancer by smell, has been shown to be...
Article
A whole new approach to artificial neural networks has received a U.S. patent. Its invention was motivated by the theoretical problem of how best to summarize activity within an extensive artificial neural system having hundreds of billions of neurons. Suspecting that this new approach to building synthetic intelligence is the same path taken by br...
Patent
Full-text available
A system for monitoring an environment may include an input device for monitoring and capturing pattern-based states of a model of the environment. The system may also include a 5 thalamobot embodied in at least a first processor, in which the first processor is in communication with the input device. The thalamobot may include at least one filter...
Article
BACKGROUND: For the past thirty years, Stephen Thaler’s work has been in the development of artificial neural networks (ANN). A major focus of his work has been to find a way to develop creativity within computers in a way that was more organic than the human-coded algorithms and rule sets used with sequential processing systems. Thaler works with...
Chapter
Although the definition of the term “creativity” widely varies, recent developments in the field of artificial neural networks (ANN) lend a highly comprehensive model to all accounts of this highly prized cognitive process. From this bottom-up, computational perspective, seminal idea formation results from a noise-driven brain storming session betw...
Article
Full-text available
Humanity has long suspected a correlation between creativity and mental illness. Those doubting such a relationship assert that psychopathologies inhibit the creative process, while others raise the issue that neither insanity nor creativity have been adequately quantified to establish such a connection. However, a new perspective has emerged throu...
Conference Paper
As neuroscience unravels the mysteries of the mind, we find that both consciousness and human nature originate collectively within the synaptic connections joining neurons. In designing an optimal body of law governing human behavior, society must be mindful of this new scientific perspective that reveals the neurodynamic mechanisms by which the br...
Article
A critical level of synaptic perturbation within a trained, artificial neural system induces the nucleation of novel activation patterns, many of which could qualify as viable ideas or action plans. In building massively parallel connectionist architectures requiring myriad, coupled neural modules driven to ideate in this manner, the need has arise...
Article
Whereas the literature is replete with findings linking creativity and various psychopathologies, the main hypothesis advanced herein is that the neurodynamics of both phenomena are the same. If vindicated, this theory may lead to advanced treatments that could potentially boost creativity as well as safeguard against the associated cognitive and p...
Article
Following the passage of the Health Information Technology for Economic and Clinical Health (HITECH) Act of 2009, electronic health records were widely adopted by eligible physicians and hospitals in the United States. Stage 2 meaningful use menu objectives include a digital family history but no stipulation as to how that information should be use...
Article
By allowing one artificial neural network to govern the synaptic noise injected into another based upon its appraisal of patterns nucleating from such disturbances, a contemplative form of artificial intelligence is formed whose creativity and pattern delivery closely parallels that of human cognition. Drawing upon the theory of fractional Brownian...
Conference Paper
In 1994 a canonical model of consciousness was proposed in which synaptic perturbations drove a multilayer perceptron through a series of activation patterns in a process that generally mimicked neurobiological stream of consciousness. Within this experimental framework, a quiescent perceptron mined this pattern flow for potentially useful confabul...
Article
Recent progress in the field of computational creativity has supplied an unanticipated model of the neurobiological knowledge management system known as the brain. Close examination of this model offers an alternative language for the field of knowledge management as well as a means for implementing cognitive agents coming closer than ever to emula...
Article
Full-text available
An artificial neural network model has been developed for predicting the perforation limits of spaced aluminium armour (aka Whipple shield) under impact of aluminium projectiles at hypervelocity. The network, utilizing a multilayer perceptron architecture, was trained on data from 769 impact tests, for which it accurately predicted the perforation...
Chapter
Although the definition of the term “creativity” widely varies, recent developments in the field of artificial neural networks (ANN) lend a highly comprehensive model to all accounts of this highly prized cognitive process. From this bottom-up, computational perspective, seminal idea formation results from a noise-driven brain storming session betw...
Conference Paper
An artificial neural network model has been developed for predicting the perforation limits of spaced aluminum armor (aka Whipple shield) under impact of aluminum projectiles at hypervelocity. The network, utilizing a multilayer perceptron architecture, was trained on data from 769 impact tests, for which it accurately predicted the perforation of...
Article
Full-text available
In Alan Turing’s landmark paper, “Computing Machinery and Intelligence,” the famous cyberneticist takes the position that machines will inevitably think, supplied adequate storage, processor speed, and an appropriate program. Herein we propose the solution to the latter prerequisite for contemplative machine intelligence, the required algorithm, il...
Conference Paper
Full-text available
The growing clash between religious dogmas is not only a significant source of discord and conflict in the world, but also a major distraction from more worthy human efforts in areas such as life extension, the equitable distribution of wealth, and more accurate systems of justice. A radically new form of synthetic intelligence not only forms the o...
Article
Full-text available
The Creativity Machine has invented new-and-improved everything from toothbrushes to warheads, and has even released an album of original music compositions ("Song of the Neurons," available on eMusic and iTunes). It may also represent the closest that inventors have come to achieving artificial intelligence and machine consciousness.
Conference Paper
Full-text available
Neural networks have been under examination for decades in many areas of research, with varying degrees of success and acceptance. Key goals of computer learning, rapid problem solution, and automatic adaptation have been elusive at best. This paper1,2 summarizes efforts at NASA's Marshall Space Flight Center harnessing such technology to autonomou...
Article
Full-text available
Neural-network modeling tools enable the engineer to study and analyze the complex interactions between material and process inputs with the goal of predicting final component properties.
Article
Full-text available
Neural-network models are mathematical tools with the goal of minimizing the error between modeled and measured output values and is designed to map input to output patterns. These models have been applied for manufacturing and metallurgical engineering. A user-friendly interface for inputting data called PatternMaster enables engineers to develop...
Conference Paper
When most hear the term “world brain,” they imagine a vast library of data residing on the Internet that is accessible by a search technology that is growing by leaps and bounds each day. However, when pressed to explain how such a resource may be described as a “brain,” and not an immense online library, no one seems to connect. After all, can a l...
Article
Artificial neural networks (ANN) were victimized by some very bad press in the mid 1980s, as some overly zealous researchers promised more than they could possibly deliver. Since that time, these unique computational devices, inspired by the very benchmark of intelligence, the human brain, are significantly more advanced in their modeling capabilit...
Patent
A system and process for readily determining, for a specified knowledge domain in a given field of endeavor, perturbations applicable to an artificial neural network embodying such a specified knowledge domain that will produce a desired output, comprising a first, previously trained, artificial neural network containing training in some problem do...
Patent
A system and process for readily determining, for a specified knowledge domain in a given field of endeavor, perturbations applicable to an artificial neural network embodying such a specified knowledge domain that will produce a desired output, comprising a first, previously trained, artificial neural network containing training in some problem do...
Article
Editor: My 1995 Neural Networks article, "'Virtual input' phenomena within the death of a simple pattern associator" addresses a heretofore unexplored connectionist topic: how any trained artificial neural network (ANN) tends to interpret its own internal damage as stored memories. The effect is investigated within a simple exemplary net and then g...
Article
Full-text available
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 kinet...
Patent
Constructing and simulating artificial neural networks and components thereof within a spreadsheet environment results in user friendly neural networks which do not require algorithmic based software in order to train or operate. Such neural networks can be easily cascaded to form complex neural networks and neural network systems, including neural...
Article
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...
Article
When an auto-associative neural network is trained within any conceptual space, the many rules and schema embodied within that knowledge domain are encoded through its many connection weights and biases. For instance, if such a network's input/output exemplars consist of numerous formulas representing known chemical compounds, subsequent network tr...
Article
Full-text available
In response to Susan Gunn's editorial, I offer a less comforting but more utilitarian perspective on the life and death of artificial consciousness. Admittedly an unpopular view, it suggests that concurrence with Gunn's message represents the seeds of our own destruction, as an emerging synthetic intelligence begins to extinguish us.
Patent
A device for simulating human creativity employing a neural network trained to produce input-output maps within some predetermined knowledge domain, an apparatus for subjecting the neural network to perturbations that produce changes in the predetermined knowledge domain, the neural network having an optional output for feeding the outputs of the n...
Conference Paper
By progressively increasing the magnitude of perturbation applied to the weights of a trained feedforward network, we observe a succession of output vectors that range between verbatim instances of training exemplars to utter nonsense. In the transition between these two extremes we observe a chaotic regime rich in unusual twists on exemplar concep...
Conference Paper
A synaptically perturbed neural network forms an efficient search engine within and around any conceptual space upon which it has been trained. By monitoring the temporal distribution of concepts emerging from such a system, we discover a quantitative agreement with the measured rhythm of human cognition, creative or otherwise. Closer examination o...
Article
A processing unit in a neural networks is representable as a collection of cells in a spreadsheet. Carrying this representation a step further results in a multinet system which trains itself in ways that resemble the processes of other types of unsupervised nets. Dynamic Data Exchange makes numerous applications of this system possible.
Conference Paper
The ability to form extensive cell reference networks within typical spreadsheet applications lends itself well to emulating the central nervous systems of simple organisms. Exploiting this capability, we have successfully created artificial neurons, neural networks, and neural network cascades within Microsoft Excel worksheets. The resulting synth...
Article
Full-text available
Contrary to the popular notion that consciousness is the result of a noble evolutionary process, I speculate that this rather ill-defined concept and phenomenon may be the result of the fragmentation of an otherwise completely connected and totally 'feeling' universe. As various regions of this universe topologically pinch-off from the whole, conne...
Article
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 fo...
Conference Paper
When the connection weights within a trained artificial neural network are randomly perturbed, the network activates through a series of both straightforward memories and hybrids thereof. This proceed, which is called network 'cavitation', thereby elicits a succession of 'internal images' in a fashion reminiscent of what is commonly called 'stream...
Article
Based upon very repeatable computer simulations of dying neural networks, the phenomena of both near-death experiences (NDEs) and a virtual afterlife are plausible and can be expected to occur in traumatized neurobiological systems. I speculate that: (1) the sociological impact of this finding is consistent with the teachings of many of the world's...
Conference Paper
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...
Conference Paper
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...
Article
A simple pattern association network, trained to convert any of eight three-bit input patterns to corresponding 3 × 3 pixel patterns, is destroyed by the random pruning of its connection weights. Within such “deaths” we see the frequent appearance of the trained output patterns independent of the application of the corresponding inputs. Such events...
Article
This paper describes a thought experiment in which a hypothetical creature created by a computer program inhabits a simple universe consisting of itself, food, and predators. As this creature "dies" it "internally" experiences these environmental features independent of their actual presence. More evolved hypothetical creatures generate novel forms...
Conference Paper
Recent breakthroughs in laser plasma techniques have allowed the rapid conversion of graphite to diamond at low pressures and the creation of other carbon phases. In this paper, the evolution from graphite to diamond is monitored via Raman spectroscopy and modeled through the use of artificial neural networks. Using such trained networks, specific...
Conference Paper
A method for potentially producing diamond-like coatings (DLC) is described in which a pulsed CO2 laser is fired into a mixture of sulfur hexafluoride and methane. The resulting laser detonation wave is used to coat windows of both ZnSe and fused silica with exceptionally adherent films. Preliminary characterization of the films suggests a dense, h...
Patent
Recent breakthroughs in laser plasma techniques have allowed the rapid conversion of graphite to diamond at low pressures and the creation of other carbon phases. In this paper, the evolution from graphite to diamond is monitored via Raman spectroscopy and modeled through the use of artificial neural networks. Using such trained networks, specific...
Chapter
The technique of Neutron Transmutation Doping (NTD) of a silicon crystal by an in-situ transmutation of the 30Si isotope into 31P via the reaction 30Si (n,γ) 31Si → 31P + β- has distinct advantages over conventional doping schemes. Among these are the precise ability to control doping concentrations and the overall uniformity of doping. The fast-ne...
Article
Through a detailed annealing study of neutron-irradiated silicon, utilizing Raman scattering, several striking trends have been observed which lend themselves to an interpretation of the annealing mechanisms in the damaged material. Most notable of these observations is the fact that the Raman intensity appears to follow separate second-order decay...
Article
Typescript. Thesis (Ph. D.)--University of Missouri--Columbia, 1982. Vita. Includes bibliographical references (leaves 136-141).
Article
A detailed study of the vibrational spectrum of neutron irradiated silicon has been carried out, utilizing laser Raman scattering. Effects due to irradiation induced defects and loss of translational invariance of the crystal lattice manifest themselves as new modes in the Raman spectra. These modes may be observed at low (120 cm-1), intermediate (...

Network

Cited By

Projects