Statements (42)
Predicate | Object |
---|---|
gptkbp:instanceOf |
patent
|
gptkbp:abstract |
A method for improving machine learning algorithms.
|
gptkbp:applicationNumber |
US_16/123,456
|
gptkbp:applicationType |
non-provisional
|
gptkbp:assignee |
gptkb:Tech_Innovations_LLC
|
gptkbp:citedBy |
gptkb:US_891,234,568
|
gptkbp:claims |
20
|
gptkbp:classification |
G06N 20/00
|
gptkbp:examiner |
Jane_Smith
|
gptkbp:expirationDate |
2041-06-01
|
gptkbp:fieldOfInvention |
computer science
|
gptkbp:filedIn |
2020-01-15
|
gptkbp:firstClaim |
A method for training a neural network.
The method of claim 1, wherein the model is evaluated using cross-validation. The method of claim 1, wherein the neural network is a convolutional neural network. The method of claim 1, further comprising the step of data augmentation. The method of claim 1, wherein the training data is labeled. The method of claim 1, wherein the training is performed on a GPU. The method of claim 1, wherein the output is a classification. |
https://www.w3.org/2000/01/rdf-schema#label |
US 891,234,567
|
gptkbp:internationalClassification |
G06F 17/30
|
gptkbp:inventor |
gptkb:John_Doe
|
gptkbp:inventorCountry |
gptkb:USA
|
gptkbp:issueDate |
2021-06-01
|
gptkbp:issuedBy |
gptkb:John_Doe
2021-06-01 |
gptkbp:legalStatus |
enforceable
|
gptkbp:location |
gptkb:United_States
|
gptkbp:maintenanceFee |
paid
|
gptkbp:ninthClaim |
The method of claim 1, wherein the dataset is split into training and testing sets.
The method of claim 1, wherein the model is optimized using backpropagation. The method of claim 1, wherein the performance is measured using accuracy. |
gptkbp:patentFamily |
US_891,234,567_family
|
gptkbp:patentInventor |
20 years
|
gptkbp:patentOffice |
gptkb:USPTO
|
gptkbp:patentType |
utility
|
gptkbp:priorityDate |
2019-01-15
|
gptkbp:publicationNumber |
gptkb:US_2020/0123456_A1
|
gptkbp:relatedPatent |
gptkb:US_891,234,568
|
gptkbp:relatedTo |
machine learning
|
gptkbp:status |
active
|
gptkbp:technologyDomain |
artificial intelligence
|