-
公开(公告)号：US20220405568A1
公开(公告)日：2022-12-22
申请号：US17304498
申请日：2021-06-22
Applicant: International Business Machines Corporation
Inventor： Andrew C. M. Hicks , Michael Terrence Cohoon
Abstract: Approaches presented herein enable determining an optimal set of machine learning algorithms for use in an artificial neural network. More specifically, a plurality of artificial neural networks is trained using a training data set. Each of the plurality of artificial neural networks has a respective unique architecture that comprises a combination of hidden layers, artificial neurons, and machine learning algorithms. Respective prediction rates of each of the plurality of artificial neural networks are compared. A best predictor artificial neural network of the plurality of artificial neural networks is identified, such that the best predictor artificial neural network has a prediction rate which is the most accurate of the respective prediction rates based on the comparing. A set of one or more machine learning algorithms used in the best predictor artificial neural network is determined.
-
公开(公告)号：US11991050B2
公开(公告)日：2024-05-21
申请号：US18049362
申请日：2022-10-25
Applicant: International Business Machines Corporation
Inventor： Andrew C. M. Hicks , Michael Terrence Cohoon
IPC: H04L41/16 , H04L41/0631
CPC classification number: H04L41/16 , H04L41/0631
Abstract: One or more systems, devices, computer program products and/or computer-implemented methods provided herein relate to data drift detection in an edge device. A system can comprise a memory configured to store computer executable components; and a processor configured to execute the computer executable components stored in the memory, wherein the computer executable components can comprise a verification component that can verify accuracy of a first model and accuracy of a second model to detect data drift associated with an edge device that is deployed without network connectivity; a computation component that can compute at least a first ratio based on the accuracy of the first model and the accuracy of the second model; and an analysis component that can use the at least the first ratio to determine whether performance degradation of at least one of the first model or the second model is a function of the data drift.
-
公开(公告)号：US11321644B2
公开(公告)日：2022-05-03
申请号：US16749015
申请日：2020-01-22
Applicant: International Business Machines Corporation
Abstract: Techniques for an expertise score vector for software component management are described herein. An aspect includes determining a size and an amount of time corresponding to committed code contributed by a first developer to a first software component. Another aspect includes determining a time per unit of contribution based on the size and amount of time. Another aspect includes updating component mastery metrics corresponding to the first software component in an expertise score vector corresponding to the first developer based on the time per unit of contribution. Another aspect includes assigning the first developer to a developer tier based on the component mastery metrics. Another aspect includes assigning a work item corresponding to the first software component to the first developer based on the developer tier.
-
公开(公告)号：US20210383006A1
公开(公告)日：2021-12-09
申请号：US16896289
申请日：2020-06-09
Applicant: International Business Machines Corporation
Inventor： Trent Matthew Balta , Anthony Thomas Sofia , Michael Terrence Cohoon , Torin Reilly
IPC: G06F21/62 , G06F16/178
Abstract: Aspects include receiving a notification that a value of a data element stored in a source storage location in a source format has been changed to an updated value. The change is replicated to a plurality of target storage locations. The replicating includes, for each of the plurality of target storage locations, determining a target format of the data element in the target storage location. The target format is one of a plurality of different formats, including the source format. Each of the different formats provide a different level of data protection for the data element. In response to determining that the target format is not the same as the source format, the updated value of the data element is converted into the target format, and the updated value of the data element is stored in the target format at the target storage location.
-
公开(公告)号：US11593498B2
公开(公告)日：2023-02-28
申请号：US16896289
申请日：2020-06-09
Applicant: International Business Machines Corporation
Inventor： Trent Matthew Balta , Anthony Thomas Sofia , Michael Terrence Cohoon , Torin Reilly
IPC: G06F21/62 , G06F16/178
Abstract: Aspects include receiving a notification that a value of a data element stored in a source storage location in a source format has been changed to an updated value. The change is replicated to a plurality of target storage locations. The replicating includes, for each of the plurality of target storage locations, determining a target format of the data element in the target storage location. The target format is one of a plurality of different formats, including the source format. Each of the different formats provide a different level of data protection for the data element. In response to determining that the target format is not the same as the source format, the updated value of the data element is converted into the target format, and the updated value of the data element is stored in the target format at the target storage location.
-
Patent Agency Ranking
公开(公告)号：US20220188627A1
公开(公告)日：2022-06-16
申请号：US17121796
申请日：2020-12-15
Applicant: International Business Machines Corporation
Inventor： Andrew C.M. Hicks , Deborah A. Furman , Michael Terrence Cohoon , MICHAEL E. GILDEIN
Abstract: Aspects of the invention include mutating each neural network of a portion of a first array of neural networks, wherein each neural network of the first array of neural networks is configured to select a respective sequence of test cases for testing a computing infrastructure. Causing each neural network of a second array of neural networks to select a respective sequence of test cases for testing the computing infrastructure. Generating a child neural network by performing a crossover operation between a mutated neural network of the portion of the first array and a neural network of the second array of neural networks, the child neural network generating a new sequence of test cases for testing the computing infrastructure.
-
公开(公告)号：US20210224719A1
公开(公告)日：2021-07-22
申请号：US16749019
申请日：2020-01-22
Applicant: International Business Machines Corporation
Abstract: Techniques for problem record management using an expertise score vector for software component management are described herein. An aspect includes receiving a problem record associated with a first work item of a software component, the first work item being associated with a first developer. Another aspect includes creating a second work item corresponding to the problem record. Another aspect includes assigning the second work item to a second developer. Another aspect includes determining that computer code from the second developer resolves the problem record. Another aspect includes, based on determining that the problem record is resolved, increasing an expertise score of the second developer.
-
公开(公告)号：US20240419704A1
公开(公告)日：2024-12-19
申请号：US18335478
申请日：2023-06-15
Applicant: International Business Machines Corporation
Inventor： Dominic Rossillo , Michael Terrence Cohoon , STEVEN LAFALCE , James A. O'Connor
IPC: G06F16/33
Abstract: In an approach, a processor preprocesses a corpus of documents of a given subject matter by: scanning each document in the corpus to identify stop words, which either is a high occurrence word that appears in at least a first pre-set threshold number of documents or a low occurrence word that appears in less than a second pre-set threshold number of documents; adding the stop words to a list of stop words; performing a spellcheck function on the corpus of documents; scanning each document in the corpus to identify subject matter relevant words based on the given subject matter; adding the identified SMR words to a list of SMR words; and assigning a weight to each identified SMR word based on a term frequency. A processor performs a similarity assessment on the corpus using the list of stop words and the list of SMR words with associated weights.
-
公开(公告)号：US20240269831A1
公开(公告)日：2024-08-15
申请号：US18169291
申请日：2023-02-15
Applicant: International Business Machines Corporation
Inventor： Sarbajit K. Rakshit , Michael Terrence Cohoon , Martin G. Keen , Jeremy R. Fox
IPC: B25J9/16
CPC classification number: B25J9/1617
Abstract: A computer system, computer readable storage medium, and computer-implemented method for operating a plurality of material handling units in a unitary configuration. The method includes determining objects to be transported from first locations to second locations. The method also includes gathering, subject to the determining the one or more objects, information with respect to characteristics of the objects. The method further includes determining, subject to the gathering of information, characteristics of a unitary material transport vehicle to transport the objects from the first locations to the second locations. The method also includes determining, subject to the determining the characteristics of the unitary material transport vehicle, a number of material handling units to form the unitary material transport vehicle. The method further includes assembling the unitary material transport vehicle. The unitary material transport vehicle includes the plurality of material handling units assembled into a unitary configuration.
-
公开(公告)号：US11501014B2
公开(公告)日：2022-11-15
申请号：US16868902
申请日：2020-05-07
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Anthony Thomas Sofia , Jason G. Katonica , Trent Matthew Balta , Michael Terrence Cohoon , Torin Reilly
Abstract: A described method includes receiving, by a database system, an instruction to change a first data element in a table in a database, which includes a first copy and a second copy of the table. A first entry is created in a first change-table. The first entry includes an updated value for a first data element. A second entry is created in a second change-table. Creating the second entry includes, changing the updated value into a ciphertext if the first data element is secured, and storing the ciphertext into the second entry. If the first data element is non-secured, the updated value is stored into the second entry as is. The second copy of the table is modified using the second change-table. The second copy of the table is used to respond to subsequent queries.
-
-
-
-
-
-
-
-
-
Search Results
20
records
(took 0.018 seconds)
