US5706401A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method for editing an input quantity for a neural network
Assignee: Siemens AG
•
Filing: 1996-08-19
•
Granted: 1998-01-06
•
Expires: 2016-08-19
Abstract
Abstract In a method for supplementing missing data in a time series used as an input to a neural network or for improving noise-infested data supplied to a neural network, error distribution densities for the missing values are calculated on the basis of the known measured values from the time series and their known or predetermined error distribution density, and samples are taken from this error distribution density according to the Monte Carlo method. These each lead to an estimated or predicted value whose average is introduced for the value to be predicted. The method can be employed for the operation as well as for the training of the neural network, and is suitable for use in all known fields of utilization of neural networks.
Inventors
- 👤 Volker Tresp
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 18:48
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/04; G06N3/08; G06N3/09
Claims Analysis
Total Claims: 14
Claim 1
Independent Claim
209 words
A method for training a computerized neural network, comprising the steps of: a) in a computer, forming a time series of a set of measured values of a variable dynamic input quantity by determining respective values of the input quantity at discrete points in time; b) in said computer, identifying a statistical noise distribution of an uncorrelated noise of finite variance that has a chronological average of zero and is superimposed on the measured values; c) in said computer, generating a substitute value for any missing measured values in the time series by, for each missing value, calculating a statistical missing value noise distribution according to said known noise distribution from at least one of said measured values neighboring the missing value in the time series and calculating said substitute value from a plurality of Monte Carlo samples of the missing value obtained according to the missing value noise distribution and replacing said missing value with said substitute value; d) supplying said time series, with the substitute value generated in step (c) replacing any missing value, from said computer to a computerized neural network as input quantities; and e) training said neural network using said time series and a behavior of a technical system represented by the neural network.
Claim 2
Independent Claim
209 words
A method for training a computerized neural network, comprising the steps of: a) in a computer, forming a time series of a set of measured values of a variable dynamic input quantity by determining respective values of the input quantity at discrete points in time; b) in said computer, identifying a statistical noise distribution of an uncorrelated noise of finite variance that has a chronological average of zero and is superimposed on the measured values; c) in said computer, generating a substitute value for any missing measured values in the time series by, for each missing value, calculating a statistical missing value noise distribution according to said known noise distribution from at least one of said measured values neighboring the missing value in the time series and calculating said substitute value from a plurality of Monte Carlo samples of the missing value obtained according to the missing value noise distribution and replacing said missing value with said substitute value; d) supplying said time series, with the substitute value generated in step (c) replacing any missing value, from said computer to a computerized neural network as input quantities; and e) training said neural network using said time series and a behavior of a technical system represented by the neural network.
Claim 3
Dependent Claim
42 words
A method according to claim 1, wherein step (c) comprises obtaining said plurality of Monte Carlo samples of the missing value according to the missing value noise distribution and determining values thereof by calculating an arithmetic average of all of said samples.
Claim 4
Dependent Claim
50 words
A method according to claim 1, wherein a value for a first of two missing and immediately neighboring measured values of the time series is generated first and a value for a second of said two missing and immediately neighboring measured values is generated thereafter using the value generated first.
Claim 5
Dependent Claim
14 words
A method according to claim 1 comprising repeating steps (a) through (b) multiple times.
Claim 6
Dependent Claim
47 words
A method according to claim 1, wherein the step of training said neural network includes, this, in a back-propagation learning step, determining a learning step width for the input quantities of the neural network normed to one by dividing the plurality of Monte Carlo samples by 0.1.
Claim 7
Dependent Claim
20 words
A method according to claim 1, where in step (b) comprises using a Gaussian distribution as said statistical noise distribution.
Claim 8
Dependent Claim
164 words
A method according to claim 1 wherein step (a) comprises forming said a time series with form: y.sub.t =f(y.sub.t-1, y.sub.t-2, . . . , y.sub.t-N)+ε.sub.t wherein ε t is said statistical noise distribution, y are measured values of the time series, y t is said missing value for which said value is to be generated by the neural network, the function f is internally available to the neural network, and wherein the statistical error distribution density is determined in step (b) as P.sub.ε (y.sub.t-1 -f(y.sub.t-1, y.sub.t-2, . . . , y.sub.t-N))=P (y.sub.t |y.sub.t-1,y.sub.t-2, . . . , y.sub.t-N) from which Monte Carlo samples y t-k l . . . y t-k s are taken and said value of the missing value to be generated by the neural network with said samples is calculated: ##EQU9## wherein y t-k are the missing measured value in the time series, k≦N, m represents all known measured values of the time series, and S is the number of samples.
Claim 9
Dependent Claim
16 words
A method according to claim 7, wherein said function f is modeled by the neural network.
Claim 10
Dependent Claim
20 words
A method according to claim 7, wherein the function f is stored in a memory accessible by the neural network.
Claim 11
Dependent Claim
110 words
A method according to claim 7 comprising the additional step of training said neural network using said time series and a behavior of a technical system represented by the neural network, including training the neural network with at least one generated value according to a learning function: ##EQU10## wherein w represents neuron weighting, L is a logarithmic probability function, η is a learning factor, and wherein ##EQU11## with NN w values of the function from the neural network, and employing measured values of the time series for y l s and, when a value is not present, P.sup.M (y.sup.l |y.sup.m) Monte Carlo samples are obtained from the probability distribution density.
Claim 12
Dependent Claim
115 words
A method according to claim 7 comprising the additional step of training said neural network using said time series and a behavior of a technical system represented by the neural network, including training the neural network with at least one generated value according to a learning function: ##EQU12## wherein w represents neuron weighting, L is a logarithmic probability function, η is a learning factor, and wherein ##EQU13## wherein NN w are values of the function from the neural network, y s 1 are measured values of the time series and wherein P.sup.M (y.sup.l |y.sup.m) Monte Carlo samples are obtained from the probability distribution density, with m representing all known measured values of the time series.
Claim 13
Independent Claim
35 words
A method according to claims 11 comprising training the neural network with a learning rule: ##EQU14## wherein w represents neuron weighting, L is a logarithmic probability function, η is a learning factor, and wherein ##EQU15##
Claim 14
Dependent Claim
170 words
A method according to claim 1, wherein the statistical noise distribution of the measured values is unknown and the measured values are superimposed with further noise having a statistical noise distribution which is known, wherein step (a) comprises forming said time series with a form: z.sub.t =y.sub.t +δ=f(y.sub.t-1,y.sub.t-2, . . . , y.sub.t-N)+ε.sub.t wherein ε t is the unknown statistical noise distribution, δ t : is the known statistical noise distribution, y: are the measured values of the time series, y t : is the value to be generated by the neural network, and wherein the statistical error distribution density is determined as: P.sub.ε (y.sub.t-1 -f(y.sub.t-1, y.sub.t-2, . . . , y.sub.t-N))=P (y.sub.t |y.sub.t-1,y.sub.t-2, . . . , y.sub.t-N) and the overall probability density over the time series is determined with: ##EQU16## and wherein step (c) comprises generating said value for said missing value by the neural network derived from at least one edited value as and obtaining Monte Carlo samples for P (y.sub.t-1, . . . , y.sub.t-N |z).
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-01-05 | 2001-07-07 | 2002-01-06 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-01-05 | 2005-07-07 | 2006-01-06 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-01-05 | 2009-07-07 | 2010-01-06 | $7700.00 | Window Closed / Lapsed |