Ordinary Fock space, defined as concatenated combination of three-dimensional spaces is the main ... more Ordinary Fock space, defined as concatenated combination of three-dimensional spaces is the main workhorse of the canonical version of quantum field theory. It is also fundamental to the modern version of quantum field theory without observers, as in the theory of Everett, Wheeler and Deutsch, which led to the theory of the universal quantum computer. It also has many practical uses, from quantum optics to the closure of turbulence and the derivation of the emergent behavior of space-time dynamical systems. But many of us believe that time and space are interchangeable to some degree, and that methods based on 4D Fock space are needed. This letter describes two simple mathematical tools to help make that possible. It discusses how computing the emergent statistics of such systems is a proper generalization of value function estimation in machine learning, which may therefore carry the same complexities with it.
Neural networks can be used to solve highly non-linear control problems. A two-layer neural net-w... more Neural networks can be used to solve highly non-linear control problems. A two-layer neural net-work containing 26 adaptive neural elements has learned to back up a computer simulated trailer truck to a loading dock, even when initially jack-knifed. It is not yet known how to ...
This chapter contains sections titled: Introduction, Neural Network Controller, Using the Baselin... more This chapter contains sections titled: Introduction, Neural Network Controller, Using the Baseline Equations, Teaching a Neural Network Using a Known Control Law, Applications, Baseline Flight and Control Equations, Performance Measures, Implementing the Baseline Aircraft Model, Training the Neural Network, Training the Neural Network via a Human Interface, Summary and Conclusions, References
This chapter contains sections titled: Adaptive Control and Robotics, Beyond Conventional Adaptiv... more This chapter contains sections titled: Adaptive Control and Robotics, Beyond Conventional Adaptive Control, Examples of Complex Robot Tasks, Extending the Tools: Challenges to Connectionism, Conclusions, References
This chapter contains sections titled: Introduction, Automated Assembly: An Example, Issues and O... more This chapter contains sections titled: Introduction, Automated Assembly: An Example, Issues and Opportunities, Acknowledgments, References
This chapter contains sections titled: Introduction, Recurrent Networks, Gradient-Based Learning ... more This chapter contains sections titled: Introduction, Recurrent Networks, Gradient-Based Learning Algorithms for Recurrent Networks, Relationship to Standard Engineering Approaches, Temporal Behavior: Three Connectionist Approaches, Significance of the Radical Approach, Conclusion, Acknowledgments, References
Neuroidentification – the effort to train neural nets to predict or simulate dynamical systems ov... more Neuroidentification – the effort to train neural nets to predict or simulate dynamical systems over time – is a key research priority, because it is crucial to efforts to design brain-like intelligent systems [1, 2, 3]. Unfortunately, most people treat this task as a simple use of supervised learning [4]: they build networks which take all of their input from a fixed set of observed variables from a fixed window of time before the prediction target. They adapt the weights in the net so as to make the outputs of the net match the prediction target for those fixed inputs, exactly as they would do in any static mapping problem. With McAvoy and Su, I have compared the long-term prediction errors which result from this procedure versus the errors which result from using a radically different training procedure – the pure robust method – to train exactly the same simple feedforward network, with the same inputs and targets. The reduction in average prediction error was 60%, across 11 predicted variables taken from 4 real-world chemical processes. More importantly, error was reduced for all variables, and reduced by a factor of 3 or more for 4 out of the 11 variables [5, p.319]. Followup work by Su[6, p.92] studied 5 more chemical processes (mostly proprietary to major manufacturers), and found that the conventional procedure simply “failed” (relative to the pure robust procedure) in 3 out of 5. This paper describes how we did it; it also tries to correct common misconceptions about recurrent networks, and summarize future research needs.
In 1981, EIA began a major study of the impact of natural gas deregulation. Through 1981, the maj... more In 1981, EIA began a major study of the impact of natural gas deregulation. Through 1981, the major product of that study was the August 1981 EIA analysis paper entitled ''Analysis of Economic Effects of Accelerated Deregulation of Natural Gas Prices.'' That paper will be referred to as the ''Deregulation Study'' below. The Natural Gas Market Model (NGMM) was the primary model used to produce the forecasts discussed in the Deregulation Study. A modified version of NGMM has been used in the initial runs of the EIA Extended Short-term Forecasting System (ESFS), which is still under development. The purpose of this paper is to provide a comprehensive description of what NGMM is, and of the inputs used with NGMM for the Deregulation Study. The Deregulation Study, and the many documentation reports it cites, contain much information about the substantive studies which led up to the forecasts; however, it does not provide enough detail on how these studies were brought together to permit either a replication or an in-depth evaluation of the forecasts. EIA standards require that models be documented in enough detail to permit replication. This report attempts to fill that gap in documentation, on the basis of a line-by-line audit of the model code, interviews with the model developers, and a replication of the model in the user-oriented system Troll. The report mentions the mechanics of how the solutions are obtained, but not in complete detail. 2 figs., 6 tabs.
Ordinary Fock space, defined as concatenated combination of three-dimensional spaces is the main ... more Ordinary Fock space, defined as concatenated combination of three-dimensional spaces is the main workhorse of the canonical version of quantum field theory. It is also fundamental to the modern version of quantum field theory without observers, as in the theory of Everett, Wheeler and Deutsch, which led to the theory of the universal quantum computer. It also has many practical uses, from quantum optics to the closure of turbulence and the derivation of the emergent behavior of space-time dynamical systems. But many of us believe that time and space are interchangeable to some degree, and that methods based on 4D Fock space are needed. This letter describes two simple mathematical tools to help make that possible. It discusses how computing the emergent statistics of such systems is a proper generalization of value function estimation in machine learning, which may therefore carry the same complexities with it.
Neural networks can be used to solve highly non-linear control problems. A two-layer neural net-w... more Neural networks can be used to solve highly non-linear control problems. A two-layer neural net-work containing 26 adaptive neural elements has learned to back up a computer simulated trailer truck to a loading dock, even when initially jack-knifed. It is not yet known how to ...
This chapter contains sections titled: Introduction, Neural Network Controller, Using the Baselin... more This chapter contains sections titled: Introduction, Neural Network Controller, Using the Baseline Equations, Teaching a Neural Network Using a Known Control Law, Applications, Baseline Flight and Control Equations, Performance Measures, Implementing the Baseline Aircraft Model, Training the Neural Network, Training the Neural Network via a Human Interface, Summary and Conclusions, References
This chapter contains sections titled: Adaptive Control and Robotics, Beyond Conventional Adaptiv... more This chapter contains sections titled: Adaptive Control and Robotics, Beyond Conventional Adaptive Control, Examples of Complex Robot Tasks, Extending the Tools: Challenges to Connectionism, Conclusions, References
This chapter contains sections titled: Introduction, Automated Assembly: An Example, Issues and O... more This chapter contains sections titled: Introduction, Automated Assembly: An Example, Issues and Opportunities, Acknowledgments, References
This chapter contains sections titled: Introduction, Recurrent Networks, Gradient-Based Learning ... more This chapter contains sections titled: Introduction, Recurrent Networks, Gradient-Based Learning Algorithms for Recurrent Networks, Relationship to Standard Engineering Approaches, Temporal Behavior: Three Connectionist Approaches, Significance of the Radical Approach, Conclusion, Acknowledgments, References
Neuroidentification – the effort to train neural nets to predict or simulate dynamical systems ov... more Neuroidentification – the effort to train neural nets to predict or simulate dynamical systems over time – is a key research priority, because it is crucial to efforts to design brain-like intelligent systems [1, 2, 3]. Unfortunately, most people treat this task as a simple use of supervised learning [4]: they build networks which take all of their input from a fixed set of observed variables from a fixed window of time before the prediction target. They adapt the weights in the net so as to make the outputs of the net match the prediction target for those fixed inputs, exactly as they would do in any static mapping problem. With McAvoy and Su, I have compared the long-term prediction errors which result from this procedure versus the errors which result from using a radically different training procedure – the pure robust method – to train exactly the same simple feedforward network, with the same inputs and targets. The reduction in average prediction error was 60%, across 11 predicted variables taken from 4 real-world chemical processes. More importantly, error was reduced for all variables, and reduced by a factor of 3 or more for 4 out of the 11 variables [5, p.319]. Followup work by Su[6, p.92] studied 5 more chemical processes (mostly proprietary to major manufacturers), and found that the conventional procedure simply “failed” (relative to the pure robust procedure) in 3 out of 5. This paper describes how we did it; it also tries to correct common misconceptions about recurrent networks, and summarize future research needs.
In 1981, EIA began a major study of the impact of natural gas deregulation. Through 1981, the maj... more In 1981, EIA began a major study of the impact of natural gas deregulation. Through 1981, the major product of that study was the August 1981 EIA analysis paper entitled ''Analysis of Economic Effects of Accelerated Deregulation of Natural Gas Prices.'' That paper will be referred to as the ''Deregulation Study'' below. The Natural Gas Market Model (NGMM) was the primary model used to produce the forecasts discussed in the Deregulation Study. A modified version of NGMM has been used in the initial runs of the EIA Extended Short-term Forecasting System (ESFS), which is still under development. The purpose of this paper is to provide a comprehensive description of what NGMM is, and of the inputs used with NGMM for the Deregulation Study. The Deregulation Study, and the many documentation reports it cites, contain much information about the substantive studies which led up to the forecasts; however, it does not provide enough detail on how these studies were brought together to permit either a replication or an in-depth evaluation of the forecasts. EIA standards require that models be documented in enough detail to permit replication. This report attempts to fill that gap in documentation, on the basis of a line-by-line audit of the model code, interviews with the model developers, and a replication of the model in the user-oriented system Troll. The report mentions the mechanics of how the solutions are obtained, but not in complete detail. 2 figs., 6 tabs.
Uploads
Papers by Paul Werbos