| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_8792b429a0730ee04cf52fceb449e033 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G05B13-027
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G05B13-0285
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-04 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G05B13-02
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
| filingDate |
1994-04-28^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8cd47b6ffb06413fc7dc7af04751c27c
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e0ae8fa21e12140af8852fc5128283a6
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4d89035a207199b49b5128863c432631 |
| publicationDate |
1994-11-10^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
WO-9425933-A1 |
| titleOfInvention |
Method and apparatus for determining the sensitivity of inputs to a neural network on output parameters |
| abstract |
A distributed control system (14) receives on the input thereof the control inputs and then outputs control signals to a plant (10) for the operation thereof. The measured variables of the plant and the contol inputs are input to a predictive model (34) that operates in conjunction with an inverse model (36) to generate predicted control inputs. The predicted control inputs are processed through a filter (46) to apply hard constrains and sensitivity modifiers, the values of which are received from a control parameter block (22). During operation, the sensitivity of output variables on various input variables is determined. This information can be displayed and then the user allowed to select which of the input variables constitute the most sensitive input variables. These can then be utilized with a control network (470) to modify the predicted values of the input variables. Additionally, a neural network (406) can be trained on only the selected input variables that are determined to be the most sensitive. In this operation, the network is first configured and trained with all input nodes and with all training data. This provides a learned representation of the output wherein the combined effects of all other input variables are taken into account in the determination of the effect of each of the input variables thereon. The network (406) is then reconfigured with only the selected inputs and then the network (406) again trained on only the input/output pairs associated with the select input variables. |
| isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-9207129-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/EP-2996001-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-9207670-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-105229541-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-2016091873-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-105229541-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-9729447-A3
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-02061678-A3
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-02061678-A2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-6859755-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-9742581-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/IT-201600125128-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-5727128-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/EP-0762245-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-9901825-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-10521716-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-9602122-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-9967602-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-9729447-A2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-8898036-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-9829785-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/FR-2765705-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-9052240-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-7228295-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-6556977-B1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-10901378-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2014190993-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-6678669-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-6272449-B1 |
| priorityDate |
1993-04-30^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |