WO2003079285A2 - Procede et systeme ainsi que programme informatique dote de moyens de code de programme et produit de programme informatique servant a ponderer des grandeurs d'entree pour une structure neuronale, ainsi que structure neuronale associee - Google Patents

Procede et systeme ainsi que programme informatique dote de moyens de code de programme et produit de programme informatique servant a ponderer des grandeurs d'entree pour une structure neuronale, ainsi que structure neuronale associee Download PDF

Info

Publication number
WO2003079285A2
WO2003079285A2 PCT/DE2003/000756 DE0300756W WO03079285A2 WO 2003079285 A2 WO2003079285 A2 WO 2003079285A2 DE 0300756 W DE0300756 W DE 0300756W WO 03079285 A2 WO03079285 A2 WO 03079285A2
Authority
WO
WIPO (PCT)
Prior art keywords
substructure
neural
dynamic
behavior
variables
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/DE2003/000756
Other languages
German (de)
English (en)
Other versions
WO2003079285A3 (fr
Inventor
Christoph Tietz
Hans-Georg Zimmermann
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Siemens Corp
Original Assignee
Siemens AG
Siemens Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens AG, Siemens Corp filed Critical Siemens AG
Publication of WO2003079285A2 publication Critical patent/WO2003079285A2/fr
Publication of WO2003079285A3 publication Critical patent/WO2003079285A3/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning

Definitions

  • the invention relates to a neural structure and a method and an arrangement as well as a computer program with program code means and a computer program product for weighting input variables for a neural structure.
  • a neural structure for example a neural network, to describe and model a dynamic process and its process behavior.
  • a dynamic process is described by a state transition description, which is not visible to an observer of the dynamic process, and an initial equation, which describes observable quantities of the technical ' dynamic process.
  • the dynamic process 200 or a dynamic system 200, in which the dynamic process runs, is subject to the influence of an external input variable u of a predeterminable dimension, an input variable u * t at a time t being designated u * t:
  • a state transition of the inner state s * t of the dynamic process is caused and the state of the dynamic process changes into a subsequent state s - ⁇ + i at a subsequent time t + 1 ,
  • f (.) denotes a general mapping rule
  • An output variable y ⁇ observable by an observer of the dynamic system 200 at a time t depends on the input variable * t and the internal state s - ⁇ -
  • the output variable yj- (yj- e 9 ⁇ n ) is predeterminable dimension n.
  • g (.) denotes a general mapping rule.
  • a neural structure of interconnected computing elements in the form of a neural network of interconnected neurons is used in [1].
  • the connections between the neurons of the neural network are weighted.
  • the weights of the neural network are summarized in a parameter vector v.
  • an internal state of a dynamic system which is subject to a dynamic process, depends on the input variable u- ⁇ and the internal state of the previous time s- ⁇ and the parameter vector v according to the following rule:
  • NN denotes a mapping rule specified by the neural network.
  • the dynamic system can also be:
  • TDRNN time delay recurrent neural network
  • the known TDRNN is shown in FIG. 5 as a neural network 500 which is developed over a finite number of times (shown 5 times: t-4, t-3, t-2, t-1, t).
  • the neural network 500 shown in FIG. 5 has an input layer 501 with five partial input layers 521, 522,
  • Input computing element i.e. Input neurons are connected via variable connections to neurons with a predefinable number of hidden layers 505 (5 hidden layers shown).
  • Neurons of a first 531, a second 532, a third 533, a fourth 534 and a fifth 535 hidden layer are each connected to neurons of the first 521, the second 522, the third 523, the fourth 524 and the fifth 525 partial input layer.
  • the connections between the first 531, the second 532, the third 533, the fourth 534 and the fifth 535 hidden layer with the first 521, the second 522, the third 523, the fourth 524 and the fifth 525 partial input layer are respectively equal.
  • the weights of all connections are each contained in a first connection matrix Bi.
  • the neurons of the first hidden layer 531 with their outputs are inputs of neurons of the second hidden layer 532 according to a structure given by a second connection matrix A ] _.
  • the neurons of the second hidden layer 532 are connected with their outputs
  • the outputs of the neurons of the third hidden layer 533 are connected to inputs of neurons of the fourth hidden layer 534 according to a structure given by the second connection matrix A] _.
  • the fourth hidden layer 534 neurons are with theirs
  • “internal” states or “internal” system states s -4 st- 3, s t-2 s t- l r and st represents a dynamic process described by the TDRNN at five successive times t-4, t-3, t-2, t-1 and t.
  • the information in the indices in the respective layers indicates the time t-4, t-3, t-2, t-1 and t, to which the signals that can be tapped or fed at the outputs of the respective layer relate ( u -4, u -3, u t-2 ' u tl' u t ) •
  • An output layer 520 has five partial output layers, a first partial output layer 541, a second partial output layer 542, a third partial output layer 543, a fourth partial output layer 544 and a fifth partial output layer
  • Neurons of the first partial output layer 541 are measured in accordance with an output connection matrix C ] _
  • Neurons of the second partial output layer 542 are e- if necessary according to the structure given by the output connection matrix C] _ with neurons of the second hidden one
  • Neurons of the third partial output layer 543 are connected to neurons of the third hidden layer 533 in accordance with the output connection matrix C] _.
  • Neurons of the fourth partial output layer 544 are connected to neurons of the fourth hidden layer 534 according to the output connection matrix C] _.
  • Neurons of the fifth partial output layer 545 are connected to neurons of the fifth hidden layer 535 in accordance with the output connection matrix C] _.
  • the output variables for a point in time t-4, t-3, t-2, t-1, t can be tapped at the neurons of the partial output layers 541, 542, 543, 544 and 545 (yt-4 * Yt-3 r Yt- 2>Yt-l> Yt) ⁇
  • connection matrices in a neural network have the same values at any given time is referred to as the principle of the so-called shared weights.
  • TDRNN Time Delay Recurrent Neural Network
  • the TDRNN is trained with the training data record.
  • An overview of various training methods can also be found in [1]. It should be emphasized at this point that only the output variables yt-4 r Yt-3 r • • • Yt can be seen at times t-4, t-3, ..., t of the dynamic system 200.
  • T is a number of times taken into account.
  • TDRNN Time Delay Recurrent Neural Network
  • Fig.la from [5] shows a basic structure on which the further developments known from [5] are based.
  • the basic structure is a neural network developed over three times t, t + 1, t + 2.
  • It has an input layer which contains a predeterminable number of input neurons, to which input variables ut can be applied at predeterminable times t, that is to say time series values described below with predefined time steps.
  • the input neurons are connected via variable connections to neurons with a predefinable number of hidden layers (3 hidden layers shown).
  • Neurons of a first hidden layer are connected to neurons of the first input layer.
  • connection between the first hidden layer and the first input layer has weights which are contained in a first connection matrix B.
  • the neurons of the first hidden layer are connected with their outputs to inputs of neurons of a second hidden layer according to a structure given by a second connection matrix A.
  • the outputs of the neurons of the second hidden layer are connected to inputs of neurons of a third hidden layer in accordance with a structure given by the second connection matrix A.
  • s st + i and st + 2 is d-described dynamic process at three successive points in time t, represents t + 1 and t + 2.
  • the details in the indices in the respective layers each indicate the time t, t + 1, t + 2, to which the signals (u- ⁇ ) which can be tapped or supplied at the outputs of the respective layer relate.
  • An output layer 120 has two sub-output layers, a first sub-output layer and a second sub-output layer. Neurons of the first partial output layer are connected to neurons of the first hidden layer in accordance with a structure given by an output connection matrix C. the. Neurons of the second partial output layer are also connected to neurons of the second hidden layer in accordance with the structure given by the output connection matrix C.
  • the output variables can be tapped at a time t + 1, t + 2 from the neurons of the partial output layers (yt + l / yt + 2 )
  • ECRNN Error Correction Recurrent Neural Networks
  • the invention is therefore based on the object of specifying a neural structure as well as a method or an arrangement or a corresponding computer program with program code means or a corresponding computer program product which differentiates, in particular a time-variant, dynamic differentiation of influencing variables of a dynamic one Systems enables.
  • the mapping behavior of which each describe a dynamic behavior of the system the first neural substructure being adapted such that its first mapping behavior describes a forward behavior of the dynamic system
  • the second neural substructure is adapted such that its second mapping behavior describes a backward behavior of the dynamic system:
  • Deviations between first input variables of the first neuronal substructure and second output variables of the second neuronal substructure are determined, which deviations represent a measure for a weighting of the influencing variables.
  • the arrangement for analyzing influencing variables of a dynamic system has a first and a second neural substructure, the mapping behavior of which describes a dynamic behavior of the system,
  • the first neural substructure is adapted such that its first mapping behavior describes a forward behavior of the dynamic system
  • the second neuronal substructure is adapted such that its second mapping behavior describes a backward behavior of the dynamic system
  • the first and the second neural substructure are coupled to one another in such a way that deviations between first input variables of the first neuronal substructure and second output variables of the second neuronal substructure are determined, which deviations represent a measure of a weighting of the influencing variables.
  • the neural structure has a first and a second neural substructure, the mapping behavior of which each describe a dynamic behavior of a dynamic system,
  • the first neural substructure being adapted such that its first mapping behavior describes a forward behavior of the dynamic system
  • the second neural substructure is adapted such that its second mapping behavior describes a backward behavior of the dynamic system
  • the first and the second neural substructure being coupled to one another in such a way that deviations between first input variables of the first neuronal substructure and second output variables of the second neuronal substructure are determined.
  • the invention clearly represents a structural one
  • Dynamic systems are usually formulated as cause-and-effect relationships (cf. comments on Fig. 2, relationships (1) to (3)), which are represented by the neuronal structures known from [1], [2] or [5] can. These cause-effect relationships are expressed in these neural structures in that an information flow generated in these neural structures moves forward in time, i.e. from the past to the future. This is called forward behavior.
  • causes of input variables ut at previous times (t- 2), (t-1), ... lead to (noticeable) effects in output variables yt at time (t or t + 1).
  • the input variables ut are mapped to the output variables yt by the neural cause-effect structure.
  • the invention extends these neural cause-effect structures with a neural substructure which carries out an effect-cause analysis and thus prepares a causal synthesis.
  • the two structures are linked by comparing actual causes with modeled causes, which are generated using the effect-cause structure, and deriving the relevance of individual external influencing factors.
  • a particular advantage of the invention is that the invention enables analysis and dynamic consideration of influencing variables of a dynamic system based on their temporal relevance ("Dynamic Feature Selection").
  • the computer program with program code means is set up to carry out all steps according to the inventive method when the program is executed on a computer.
  • the computer program product with program code means stored on a machine-readable carrier is set up to carry out all steps according to the inventive method when the program is executed on a computer.
  • the described software solutions can also be implemented decentrally or distributed, i.e. that parts of the computer program or parts of the computer program product - also as independent partial solutions - run on different (distributed) computers or are executed by them or are stored on different storage media.
  • the invention or any further development described below can also be implemented by a computer program product which has a storage medium on which the computer program with program code means which carries out the invention or further development is stored.
  • the first and / or the second neural substructure is or are a neural network developed over several points in time, for example a TDRNN, or neural networks unfolded over several points in time, in which one or in which a temporal dimension of the described one dynamic system is developed as a spatial dimension.
  • the first are used to implement automatic, time-variant and dynamic weighting of the influencing variables
  • Input variables of the first neural substructure are weighted using the deviations.
  • the invention is particularly suitable for determining the dynamics of a dynamic process on which the system is based.
  • the dynamics result from the first output variables of the first neural substructure.
  • Chemical processes are usually highly complex or highly complex dynamic processes and are influenced by many physical variables. Accordingly, the invention is particularly suitable for determining and analyzing the dynamics of a dynamic process, such as in a chemical reactor. This analysis can then be used to monitor or control the dynamic process, in particular a chemical process.
  • the invention is particularly suitable for predicting a state of the dynamic system.
  • the forecast is created using the first output variables of the first substructure.
  • the invention has a measuring arrangement for recording physical signals, for example an electrocardio gram (EKG), by means of which the dynamic system, in this case a human circulation, is described. These physical signals, the EKG signals, are then fed to the first neuronal substructure for analyzing the system.
  • EKG electrocardio gram
  • first neural substructure and the second neural substructure can be coupled such that further deviations can be formed between first output variables of the first neuronal substructure and second input variables of the second neuronal substructure.
  • the first and / or second neural substructure is / are designed as an error correction recurrent neural network (ECRNN). Fundamentals of such ECRNN are described in [6] and can be built into the neural substructures accordingly.
  • ECRNN error correction recurrent neural network
  • FIG. 2 shows a sketch of a general description of a dynamic system
  • FIG. 3 shows a sketch of a neural arrangement with an integrated error correction mechanism according to a second exemplary embodiment (note: corresponds to slide pta_5 / 20);
  • FIG. 4 shows a sketch of a chemical reactor, from which quantities are measured, which are processed further with the arrangements according to the first exemplary embodiment
  • FIG. 5 shows a sketch of an arrangement of a TDRNN, which is unfolded over time with a finite number of states (note: from old application 99pl348);
  • FIG. 6 shows a sketch of a further development of a TDRNN suitable for the “overshooting” (note: corresponds to slide pta_5 / 7),
  • Figure 7 is a sketch of an ECRNN with basic functional relationships (note: corresponds to slide pta_5 / 10).
  • FIG. 8 shows a sketch of a neural arrangement with an integrated error correction mechanism according to a second
  • Exemplary embodiment (note: corresponds to film pta 5/22).
  • chemical reactor 4 shows a chemical reactor 400 which is filled with a chemical substance 401.
  • the chemical reactor 400 comprises a stirrer 402 with which the chemical substance 401 is stirred. Further chemical substances 403 flowing into the chemical reactor 400 react for a predeterminable period in the chemical reactor 400 with the chemical substance 401 already contained in the chemical reactor 400. A substance 404 flowing out of the reactor 400 is transferred from the chemical reactor 400 derived an output.
  • the stirrer 402 is connected via a line to a control unit 405, with which a stirring frequency of the stirrer 402 can be set via a control signal 406.
  • a measuring device 407 is also provided, with which concentrations of chemical substances contained in chemical substance 401 are measured.
  • Measurement signals 408 are fed to a computer 409, in which
  • Computer 409 is digitized via an input / output interface 410 and an analog / digital converter 411 and stored in a memory 412.
  • a processor 413 like the memory 412, is connected to the analog / digital converter 411 via a bus 414.
  • the calculator 409 is also on the
  • Input / output interface 410 connected to the controller 405 of the stirrer 402 and thus the computer 409 controls the stirring frequency of the stirrer 402.
  • the computer 409 is also connected via the input / output interface 410 to a keyboard 415, a computer mouse 416 and a screen 417.
  • appropriately programmed software is stored in the memory. 412, which enables the functionality described below.
  • the chemical reactor 400 represents a dynamic, technical system 200 and is subject to a dynamic process on which the dynamic system is based.
  • This chemical process is highly complex and exhibits extremely dynamic process behavior, which is influenced by a large number of influencing variables with changing relevance.
  • the chemical reactor 400 is described by means of a status description.
  • the input variable u is composed of an indication of the temperature prevailing in the chemical reactor 400, the pressure prevailing in the chemical reactor 400, the stirring frequency set at the time t and a large number of other variables influencing the process behavior.
  • the input variable is therefore a high-dimensional vector.
  • the aim of the modeling of the chemical reactor 400 described in the following is to determine the dynamic development of the substance concentrations, in order to enable efficient generation of a predefinable target substance to be produced as the outflowing substance 404.
  • FIG. 1b 130 and 1c 160 For a simple understanding of the principles underlying the neural networks FIGS. 1b 130 and 1c 160, a basic neural structure 100 is shown in FIG.
  • the neural networks 130, 160 shown in FIGS. 1b and 1c are formed.
  • the neural networks 130 (Consistency Approach), 160 (Forecast Appraoch) shown in FIGS. 1b and 1c are all can be used alternatively. Each fulfills the task described above ("Dynamic Feature Selection") equally.
  • the symbols used in the representation correspond to the generally customary symbolism in the representation of neural structures, as already used in the above network descriptions.
  • FIG. 1 a shows the neural basic structure 100 with a first neural substructure 101, the first mapping behavior of which describes a forward behavior 103 of the dynamic process or system.
  • First input variables 111 are mapped to first output variables 112 by the first neural substructure 101.
  • the neural basic structure 100 has a second neural substructure 102, the second mapping behavior of which describes a backward behavior 104 of the dynamic system. Second input variables 113 are mapped to second output variables 114 by the second neural substructure 101.
  • the substructures 101, 102 are coupled to one another in such a way that deviations 120 between the first input variables 111 of the first neuronal structure 101 and the second output variables 114 of the second neuronal structure 102 can be determined.
  • weights 121 are determined with which the first input variables 111 supplied to the first substructure 101 are weighted.
  • 1b shows a neural network 130 based on the neural basic structure 100 according to the consistency appraoch.
  • the neural network 130 has a first neural substructure 131 and a second neural substructure 132, each of which over several points in time t, here (t-3) to (t + 3) at the first 131 or (t) to (t- 3) in the second neural substructure 132, are unfolded recurrent networks.
  • the two neural networks 131, 132 each have an input neuron layer 133 and 134, a hidden neuron layer 135 and 136, and an output neuron layer 137 and 138, respectively.
  • the input neuron layers 133 and 134 are each connected to the hidden layers 135 and 136 via connections weighted with connection matrices B and E, respectively.
  • connection matrices A and F weighted connections are in turn connected by connection matrices A and F weighted connections.
  • the output neuron layers 137 and 138 are each connected to the hidden layers 135 and 136 via connections weighted with connection matrices C and G, respectively.
  • ATU an intermediate layer of neurons 140, wweellcchhee wwiitthh eeiinneerr GGee ⁇ weighting at weighted states, / _. generated, fed This intermediate neuron layer 140 is connected to the hidden layer 135 via connections weighted with connection matrices D.
  • the output neuron layer 138 of the second substructure 132 is further connected to the input neuron layer 133 of the first substructure 131 via connections weighted with connection matrices H.
  • the neuron links are designed in such a way that a forward-looking information flow 141, represented by states st-3, ⁇ t-2 / s tl ' s t etc., is generated in the hidden layer 135 of the first substructure 131.
  • Substructure 132 generates a backward-directed information flow 142, represented by states rt, r * t_ ⁇ , rt-2 ' r t-3.
  • the neural network 130 described is based on the following relationships:
  • a method based on a back-propagation method, as described in [1], is used for training the neural network 130 described above.
  • T is a number of times taken into account.
  • the cost function is modified to:
  • T t lf, g, F, G y t - y t ): upper minimum output error, u ⁇ - U): lower minimum input error.
  • the difference states u t - u?) Formed in the output layer 138 of the second substructure 132 are components of the cost function (10).
  • Training data for the training according to (5) are obtained from the chemical reactor 400 in the following way.
  • Concentrations are measured using the measuring device 407 for predetermined input variables and fed to the computer 409, digitized there and grouped as time series values in a memory together with the corresponding input variables which correspond to the measured variables.
  • the training data are fed to the neural network 130 and the connection weights and also the weight at are adapted in the process.
  • the neural network 130 trained in accordance with the training method described above is used to determine chemical variables in the chemical reactor 400 in such a way that forecast variables yt + i yt + 2 yt + 3 n for an input variable at a time t-1 and an input variable at a time t e ner
  • control means 405 for controlling the stirrer 402 or also an inflow control device 430 for controlling the inflow of further chemical substances 403 in the chemical reactor 400 can be used (see Fig. 4).
  • Forecast Approach (Fig.lc, 160) 1c shows the alternative neural structure 160 based on the neural basic structure 100 according to the forecast approach.
  • This neural network 160 is based on the following relationships:
  • the structure of the neural network 160 according to the forecast approach is identical to that of the consistency approach 130.
  • Two neural networks 131 and 132 developed over several points in time, one with a forward-looking 141 and one with a backward-looking 142 information flow, are about a "difference states" Layer 138, a weighting neuron 139 and a weighting layer 140 are linked to one another.
  • the training of the neural network 160 and the use of the neural network 160 in the application are carried out in accordance with the neural network 130.
  • FIG. 3 shows a neural structure 300 in which the error described in [6] in the neural structure from FIG. Correction mechanism (ECRNN) was integrated (ECRNN Forecast Approach).
  • ERNN Correction mechanism
  • the neural structure 300 is used for a rental price forecast as described below.
  • the input variable u * t is made up of annual average information about a rental price, housing space, inflation and an unemployment rate, as well as other economic factors that influence a rental price.
  • the input variable is a high-dimensional vector.
  • a time series of the input variables which consist of several successive vectors, knows time steps of one year each.
  • the aim of the modeling described below is to forecast a rental price for the following three years with respect to a current point in time t.
  • the neural structure 300 in FIG. 3 shows the neural structure 160 expanded by the error correction mechanism (ECRNN) based on the neural basic structure 100 according to the forecast approach.
  • ERNN error correction mechanism
  • This neural network 300 is based on the following relationships:
  • the structure of the neural network 300 according to the ECRNN Forecast Approach is identical to that of the Forecast Approach 160 and the Consistency Approach 130.
  • the training of the neural network 300 is carried out in accordance with the neural networks 130 and 161. Further procedures for training the neural network described above are described in [4].
  • FIG. 8 shows an alternative neuronal ERCNN structure based on the neuronal structure in FIG. 3.
  • This alternative neural structure like the neural structures described in the exemplary embodiments, contain the inventive principles for dynamic feature selection, so that the above explanations apply accordingly.
  • the arrangements described in the first exemplary embodiment can also be used to determine the dynamics of an electronic Cardio-grams (EKG) can be used. This enables indicators that indicate an increased risk of heart attack to be determined at an early stage. A time series from ECG values measured on a patient is used as the input variable.
  • EKG electronic Cardio-grams
  • the arrangement described in the second exemplary embodiment can also be used for forecasting macroeconomic dynamics, such as, for example, an exchange rate trend, or other economic indicators, such as, for example, a stock exchange price.
  • macroeconomic dynamics such as, for example, an exchange rate trend, or other economic indicators, such as, for example, a stock exchange price.
  • an input variable is formed from time series of relevant macroeconomic or economic indicators, such as interest rates, currencies or inflation rates.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Length Measuring Devices With Unspecified Measuring Means (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Structure neuronale pour la modélisation d'un système dynamique, ladite structure permettant une pondération automatique et variable dans le temps de grandeurs d'influence du système. A cet effet, ladite structure neuronale possède une première structure neuronale partielle dont le premier comportement de représentation décrit un comportement vers l'avant du système dynamique et une seconde structure neuronale partielle dont le second comportement de représentation décrit un comportement vers l'arrière du système dynamique. Lesdites structures partielles sont couplées l'une à l'autre de manière telle que des écarts entre des premières grandeurs d'entrée de la première structure neuronale et des secondes grandeurs de sortie de la seconde structure neuronale peuvent être déterminés, la pondération pouvant être opérée à l'aide desdits écarts.
PCT/DE2003/000756 2002-03-20 2003-03-10 Procede et systeme ainsi que programme informatique dote de moyens de code de programme et produit de programme informatique servant a ponderer des grandeurs d'entree pour une structure neuronale, ainsi que structure neuronale associee Ceased WO2003079285A2 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE10212408 2002-03-20
DE10212408.6 2002-03-20

Publications (2)

Publication Number Publication Date
WO2003079285A2 true WO2003079285A2 (fr) 2003-09-25
WO2003079285A3 WO2003079285A3 (fr) 2004-09-10

Family

ID=27815812

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/DE2003/000756 Ceased WO2003079285A2 (fr) 2002-03-20 2003-03-10 Procede et systeme ainsi que programme informatique dote de moyens de code de programme et produit de programme informatique servant a ponderer des grandeurs d'entree pour une structure neuronale, ainsi que structure neuronale associee

Country Status (1)

Country Link
WO (1) WO2003079285A2 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012113634A1 (fr) * 2011-02-24 2012-08-30 Siemens Aktiengesellschaft Procédé d'apprentissage assisté par ordinateur d'un réseau neuronal récurrent pour la modélisation d'un système dynamique
CN117035101A (zh) * 2023-07-20 2023-11-10 常州大学 基于自治神经元多涡卷吸引子控制方法及系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5402519A (en) * 1990-11-26 1995-03-28 Hitachi, Ltd. Neural network system adapted for non-linear processing
JP3070643B2 (ja) * 1992-10-23 2000-07-31 株式会社デンソー ニューラルネット型追加学習装置
US6493691B1 (en) * 1998-08-07 2002-12-10 Siemens Ag Assembly of interconnected computing elements, method for computer-assisted determination of a dynamics which is the base of a dynamic process, and method for computer-assisted training of an assembly of interconnected elements

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012113634A1 (fr) * 2011-02-24 2012-08-30 Siemens Aktiengesellschaft Procédé d'apprentissage assisté par ordinateur d'un réseau neuronal récurrent pour la modélisation d'un système dynamique
CN117035101A (zh) * 2023-07-20 2023-11-10 常州大学 基于自治神经元多涡卷吸引子控制方法及系统
CN117035101B (zh) * 2023-07-20 2024-02-13 常州大学 基于自治神经元多涡卷吸引子控制方法及系统

Also Published As

Publication number Publication date
WO2003079285A3 (fr) 2004-09-10

Similar Documents

Publication Publication Date Title
EP2112568B1 (fr) Procédé de commande et/ou réglage assistées par ordinateur d'un système technique
EP1145192B1 (fr) Configuration d'elements informatiques interconnectes, procede de determination assistee par ordinateur d'une dynamique a la base d'un processus dynamique et procede d'apprentissage assiste par ordinateur d'une configuration d'elements informatiques interconnectes
EP3970113B1 (fr) Détermination du niveau d'usure d'un outil
WO2000008599A2 (fr) Ensemble d'elements de calcul relies les uns aux autres, procede de determination assistee par ordinateur d'une dynamique a la base d'un processus dynamique, et procede d'entrainement assiste par ordinateur pour un ensemble d'elements de calcul relies les uns aux autres
DE102007026314A1 (de) Verfahren zur Steuerung und/oder Regelung eines Brennstoffzellensystems
EP2433185B1 (fr) Dispositif et procédé pour le traitement d'une base de données de simulation d'un processus
EP1252566B1 (fr) Configuration d'elements de calcul interconnectes et procede de determination assistee par ordinateur du deuxieme etat d'un systeme dans un premier espace d'etat a partir d'un premier etat du systeme dans le premier espace d'etat
DE19734947A1 (de) Verfahren zur Steuerung von Prozeßvorgängen
EP1055180B1 (fr) Procede et dispositif de conception d'un systeme technique
EP1627263B1 (fr) Procede et programme informatique comportant des moyens de code de programme et programme informatique pour determiner un comportement futur d'un systeme dynamique
DE102006058423A1 (de) Verfahren und Systeme zur vorhersagenden Modellierung unter Nutzung eines Modellkollektivs
EP0978052B1 (fr) Selection assistee par ordinateur de donnees d'entrainement pour reseau neuronal
DE69328596T2 (de) Optimierung eines Neuralnetzwerks mit Vorwärtskopplung
WO2003079285A2 (fr) Procede et systeme ainsi que programme informatique dote de moyens de code de programme et produit de programme informatique servant a ponderer des grandeurs d'entree pour une structure neuronale, ainsi que structure neuronale associee
EP1145190B1 (fr) Ensemble de plusieurs elements de calcul relies entre eux, procede de determination assistee par ordinateur d'une dynamique se trouvant a la base d'un processus dynamique et procede pour l'entrainement assiste par ordinateur d'un ensemble d'elements de calcul relies entre eux
EP4605762A1 (fr) Procédé de détection de circuits parallèles dans des dispositifs d'alimentation électrique
EP1114398A2 (fr) Procede pour entrainer un reseau neuronal, procede de classification d'une sequence de grandeurs d'entree au moyen d'un reseau neuronal, reseau neuronal et dispositif pour l'entrainement d'un reseau neuronal
DE102020106857A1 (de) Mikroskopiesystem und verfahren zum verarbeiten von mikroskopbildern
EP1196828B1 (fr) Procede et dispositif pour pretraitement
EP1190383B1 (fr) Procede de determination assistee par ordinateur de l'appartenance d'une grandeur d'entree donnee a un groupe
EP1194890B1 (fr) Dispositif, procede, produit comportant un programme d'ordinateur et support de stockage lisible par ordinateur pour la compensation assistee par ordinateur d'un etat de desequilibre d'un systeme technique
DE19742902A1 (de) Verfahren zur Planung und Durchführung von Versuchen
DE102021205097A1 (de) Computerimplementiertes Verfahren und System zur Bestimmung einer Kostenfunktion
WO2021105114A1 (fr) Procédé de détermination d'un modèle stationnaire d'un système technique
DE102021205098A1 (de) Computerimplementiertes Verfahren und System zur Bestimmung einer Kostenfunktion

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): JP US

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PT RO SE SI SK TR

121 Ep: the epo has been informed by wipo that ep was designated in this application
DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
122 Ep: pct application non-entry in european phase
NENP Non-entry into the national phase

Ref country code: JP

WWW Wipo information: withdrawn in national office

Country of ref document: JP