Results 1  10
of
30
Realtime neuroevolution in the nero video game
 IEEE Transactions on Evolutionary Computation
, 2005
"... In most modern video games, character behavior is scripted; no matter how many times the player exploits a weakness, that weakness is never repaired. Yet if game characters could learn through interacting with the player, behavior could improve as the game is played, keeping it interesting. This pap ..."
Abstract

Cited by 89 (32 self)
 Add to MetaCart
(Show Context)
In most modern video games, character behavior is scripted; no matter how many times the player exploits a weakness, that weakness is never repaired. Yet if game characters could learn through interacting with the player, behavior could improve as the game is played, keeping it interesting. This paper introduces the realtime NeuroEvolution of Augmenting Topologies (rtNEAT) method for evolving increasingly complex artificial neural networks in real time, as a game is being played. The rtNEAT method allows agents to change and improve during the game. In fact, rtNEAT makes possible an entirely new genre of video games in which the player trains a team of agents through a series of customized exercises. To demonstrate this concept, the NeuroEvolving Robotic Operatives (NERO) game was built based on rtNEAT. In NERO, the player trains a team of virtual robots for combat against other players ’ teams. This paper describes results from this novel application of machine learning, and demonstrates that rtNEAT makes possible video games like NERO where agents evolve and adapt in real time. In the future, rtNEAT may allow new kinds of educational and training applications through interactive and adapting games. 1
Computational aspects of feedback in neural circuits
 PLOS Computational Biology
, 2007
"... It has previously been shown that generic cortical microcircuit models can perform complex realtime computations on continuous input streams, provided that these computations can be carried out with a rapidly fading memory. We investigate the computational capability of such circuits in the more re ..."
Abstract

Cited by 21 (5 self)
 Add to MetaCart
(Show Context)
It has previously been shown that generic cortical microcircuit models can perform complex realtime computations on continuous input streams, provided that these computations can be carried out with a rapidly fading memory. We investigate the computational capability of such circuits in the more realistic case where not only readout neurons, but in addition a few neurons within the circuit, have been trained for specific tasks. This is essentially equivalent to the case where the output of trained readout neurons is fed back into the circuit. We show that this new model overcomes the limitation of a rapidly fading memory. In fact, we prove that in the idealized case without noise it can carry out any conceivable digital or analog computation on timevarying inputs. But even with noise, the resulting computational model can perform a large class of biologically relevant realtime computations that require a nonfading memory. We demonstrate these computational implications of feedback both theoretically, and through computer simulations of detailed cortical microcircuit models that are subject to noise and have complex inherent dynamics. We show that the application of simple learning procedures (such as linear regression or perceptron learning) to a few neurons enables such circuits to represent time over behaviorally relevant long time spans, to integrate evidence from incoming spike trains over longer periods of time, and to process new information contained in such spike trains in diverse ways according to the current internal state of the circuit. In particular we show that such generic cortical microcircuits with feedback provide a new model for working memory that is consistent with a large set of biological constraints.
A theory of complexity for continuous time systems
 Journal of Complexity
, 2002
"... We present a model of computation with ordinary differential equations (ODEs) which converge to attractors that are interpreted as the output of a computation. We introduce a measure of complexity for exponentially convergent ODEs, enabling an algorithmic analysis of continuous time flows and their ..."
Abstract

Cited by 19 (0 self)
 Add to MetaCart
(Show Context)
We present a model of computation with ordinary differential equations (ODEs) which converge to attractors that are interpreted as the output of a computation. We introduce a measure of complexity for exponentially convergent ODEs, enabling an algorithmic analysis of continuous time flows and their comparison with discrete algorithms. We define polynomial and logarithmic continuous time complexity classes and show that an ODE which solves the maximum network flow problem has polynomial time complexity. We also analyze a simple flow that solves the Maximum problem in logarithmic time. We conjecture that a subclass of the continuous P is equivalent to the classical P. 2001 Elsevier Science (USA) Key Words: theory of analog computation; dynamical systems.
The many forms of hypercomputation
 Applied Mathematics and Computation
, 2006
"... This paper surveys a wide range of proposed hypermachines, examining the resources that they require and the capabilities that they possess. ..."
Abstract

Cited by 17 (0 self)
 Add to MetaCart
(Show Context)
This paper surveys a wide range of proposed hypermachines, examining the resources that they require and the capabilities that they possess.
The simple dynamics of super Turing theories
, 1994
"... This paper reasons about the need to seek for particular kinds of models of computation that imply stronger computability than the classical models. A possible such model, constituting a chaotic dynamical system, is presented. This system, which we term as the analog shift map, when viewed as a comp ..."
Abstract

Cited by 16 (0 self)
 Add to MetaCart
(Show Context)
This paper reasons about the need to seek for particular kinds of models of computation that imply stronger computability than the classical models. A possible such model, constituting a chaotic dynamical system, is presented. This system, which we term as the analog shift map, when viewed as a computational model has superTuring power and is equivalent to neural networks and the class of analog machines. This map may be appropriate to describe idealized physical phenomena. 1.
Investigations into Information Semantics and Ethics of Computing, Mälardalen University Press, http://www.diva‐portal.org/mdh/theses/abstract.xsql?dbid=153 Dodig‐Crnkovic, G. (2008) Knowledge Generation as Natural Computation
 Information Science Reference
, 2006
"... The recent development of research field of Computing and Philosophy and especially its Philosophy of Information (PI) branch has spurred investigations of philosophical, methodological and ethical foundations of computing. This thesis is a result of studies into two basic areas of PI that concern m ..."
Abstract

Cited by 13 (6 self)
 Add to MetaCart
The recent development of research field of Computing and Philosophy and especially its Philosophy of Information (PI) branch has spurred investigations of philosophical, methodological and ethical foundations of computing. This thesis is a result of studies into two basic areas of PI that concern meaning (semantics) and underlying value system (ethics). The aim is, among others, to encompass those both views within the common ground, and to indicate the necessity to bring those two fields together in a holistic characterization of computing as a discipline. In general, a method of conceptual integration is used in order to bridge gaps between different disciplines like different branches of philosophy, computing (including theory of computation, intelligent systems, cognitive science, information science, knowledge management), natural science (physics and biology in the first place) and even methodology of science. The first gives first the general view of the new emerging scientific paradigm shift that is going on parallel with the ubiquitous computing. Computing is characterized as a new discipline with the potential of starting a new Renaissance – bringing together sciences, technology, humanities, arts and practical activities into a new holistic worldview. We do not see the Universe nowadays as Laplacean
Stochastic analog networks and computational complexity
 J. Complexity
, 1999
"... The model of analog recurrent neural networks (ARNN) is typically perceived as based on either the practical powerful tool of automatic learning or on biological metaphors, yet it constitutes an appealing model of computation. This paper provides rigorous foundations for ARNN, when they are allowed ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
(Show Context)
The model of analog recurrent neural networks (ARNN) is typically perceived as based on either the practical powerful tool of automatic learning or on biological metaphors, yet it constitutes an appealing model of computation. This paper provides rigorous foundations for ARNN, when they are allowed to exhibit stochastic and random behavior of discrete nature. Our model is an extension of the von Neumann model of unreliable interconnection of components and incorporates a generalization of Shannon's randomnoise philosophy. In the general case the computational class (P poly) is associated with both deterministic and stochastic networks. However, when the weights are restricted to rational numbers, stochasticity adds power to the computation. As part of the proof, we show that probabilistic Turing machines that use a coin with a real probability rather than an) coin, compute the nonuniform version BPP log * instead of the exactly random ( 1 2 recursive class BPP. We also show that in the case of real probabilities only their first logarithmic number of bits are relevant for the computation. 1999 Academic Press 1.
Zhang Z. Shorthorizon prediction of wind power: a datadriven approach
 IEEE Transactions on Energy Conversion
"... Abstract—This paper discusses shorthorizon prediction of wind speed and power using wind turbine data collected at 10 s intervals. A timeseries model approach to examine wind behavior is studied. Both exponential smoothing and datadriven models are developed for wind prediction. Power prediction ..."
Abstract

Cited by 4 (3 self)
 Add to MetaCart
(Show Context)
Abstract—This paper discusses shorthorizon prediction of wind speed and power using wind turbine data collected at 10 s intervals. A timeseries model approach to examine wind behavior is studied. Both exponential smoothing and datadriven models are developed for wind prediction. Power prediction models are established, which are based on the most effective wind prediction model. Comparative analysis of the power predicting models is discussed. Computational results demonstrate performance advantages provided by the datadriven approach. All computations reported in the paper are based on the data collected at a large wind farm. Index Terms—Data mining, evolutionary strategy (ES) algorithm, exponential smoothing, neural networks (NNs), power prediction, timeseries model, wind speed prediction. I.
Adaptive control of a wind turbine with data mining and swarm intelligence
 IEEE Trans. Sustain. Energy
"... Abstract—The framework of adaptive control applied to a wind turbine is presented. The wind turbine is adaptively controlled to achieve a balance between two objectives, power maximization and minimization of the generator torque ramp rate. An optimization model is developed and solved with a linear ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
(Show Context)
Abstract—The framework of adaptive control applied to a wind turbine is presented. The wind turbine is adaptively controlled to achieve a balance between two objectives, power maximization and minimization of the generator torque ramp rate. An optimization model is developed and solved with a linear weighted objective. The objective weights are autonomously adjusted based on the demand data and the predicted power production. Two simulation models are established to generate demand information. The wind power is predicted by a datadriven timeseries model utilizing historical wind speed and generated power data. The power generated from the wind turbine is estimated by another model. Due to the intrinsic properties of the datadriven model and changing weights of the objective function, a particle swarm fuzzy algorithm is used to solve it. Index Terms—Adaptive control, blade pitch angle, data mining, electricity demand simulation, generator torque, neural networks, optimization, particle swarm fuzzy algorithm, power prediction. I.
Analysis of wind turbine vibrations based on SCADA data
 ASME J. Sol. Eng
, 2010
"... Vibrations of a wind turbine have a negative impact on its performance. Mitigating this undesirable impact requires knowledge of the relationship between the vibrations and other wind turbine parameters that could be potentially modified. Three approaches for ranking the impact importance of measura ..."
Abstract

Cited by 3 (3 self)
 Add to MetaCart
Vibrations of a wind turbine have a negative impact on its performance. Mitigating this undesirable impact requires knowledge of the relationship between the vibrations and other wind turbine parameters that could be potentially modified. Three approaches for ranking the impact importance of measurable turbine parameters on the vibrations of the drive train and the tower are discussed. They include the predictor importance analysis, the global sensitivity analysis, and the correlation coefficient analysis versed in data mining and statistics. To decouple the impact of wind speed on the vibrations of the drive train and the tower, the analysis is performed on data sets with narrow speed ranges. Wavelet analysis is applied to filter noisy accelerometer data. To exclude the impact malfunctions on the vibration analysis, the data are analyzed in a frequency domain. Datamining algorithms are used to build models with turbine parameters of interest as inputs, and the vibrations of drive train and tower as outputs. The performance of each model is thoroughly evaluated based on metrics widely used in the wind industry. The neural network algorithm outperforms other classifiers and is considered to be the most promising approach to study wind turbine vibrations. �DOI: 10.1115/1.4001461�