公开(公告)号：ZA202100290B

公开(公告)日：2022-01-26

申请号：ZA202100290

申请日：2021-01-15

Applicant: IBM

Inventor： RIEGEL RYAN ,  LUUS FRANCOIS PIERRE ,  AKHALWAYA ISMAIL YUNUS ,  KHAN NAWEED ,  MAKONDO NDIVHUWO ,  BARAHONA FRANCISCO ,  GRAY ALEXANDER

Abstract: A system for configuring and using a logical neural network including a graph syntax tree of formulae in a represented knowledgebase connected to each other via nodes representing each proposition. One neuron exists for each logical connective occurring in each formula and, additionally, one neuron for each unique proposition occurring in any formula. All neurons return pairs of values representing upper and lower bounds on truth values of their corresponding subformulae and propositions. Neurons corresponding to logical connectives accept as input the output of neurons corresponding to their operands and have activation functions configured to match the connectives' truth functions. Neurons corresponding to propositions accept as input the output of neurons established as proofs of bounds on the propositions' truth values and have activation functions configured to aggregate the tightest such bounds. Bidirectional inference permits every occurrence of each proposition in each formula to be used as a potential proof.

公开(公告)号：AU2021269906A1

公开(公告)日：2022-10-27

申请号：AU2021269906

申请日：2021-04-13

Applicant: IBM

Inventor： RIEGEL RYAN ,  LUUS FRANCOIS ,  AKHALWAYA ISMAIL YUNUS ,  KHAN NAWEED AGHMAD ,  MAKONDO NDIVHUWO ,  BARAHONA FRANCISCO ,  GRAY ALEXANDER

IPC: G06N3/04

Abstract: A system for configuring and using a logical neural network including a graph syntax tree of formulae in a represented knowledgebase connected to each other via nodes representing each proposition. One neuron exists for each logical connective occurring in each formula and, additionally, one neuron for each unique proposition occurring in any formula. All neurons return pairs of values representing upper and lower bounds on truth values of their corresponding subformulae and propositions. Neurons corresponding to logical connectives accept as input the output of neurons corresponding to their operands and have activation functions configured to match the connectives' truth functions. Neurons corresponding to propositions accept as input the output of neurons established as proofs of bounds on the propositions' truth values and have activation functions configured to aggregate the tightest such bounds. Bidirectional inference permits every occurrence of each proposition in each formula to be used as a potential proof.

公开(公告)号：ZA201805778B

公开(公告)日：2019-06-26

申请号：ZA201805778

申请日：2018-08-29

Applicant: IBM

Inventor： VARUGHESE MELVIN MATHEW ,  AKHALWAYA ISMAIL YUNUS ,  OBROCKA MONIKA ,  LUUS FRANCOIS PIERRE SAREL ,  ANIYAN ARUN

公开(公告)号：ZA202102725B

公开(公告)日：2022-08-31

申请号：ZA202102725

申请日：2021-04-23

Applicant: IBM

Inventor： LUUS FRANCOIS PIERRE ,  VOS ETIENNE EBEN ,  MAKONDO NDIVHUWO ,  KHAN NAWEED AGHMAD ,  AKHALWAYA ISMAIL YUNUS

Abstract: An ontology topic is selected and a pretrained predictive language model is primed to create a predictive primed model based on one or more ontological rules corresponding to the selected ontology topic. Using the predictive primed model, natural language text is generated based on the ontology topic and guidance of a prediction steering component. The predictive primed model is guided in selecting text that is predicted to be appropriate for the ontology topic and the generated natural language text. The generated natural language text is processed to generate extracted ontology rules and the extracted ontology rules are compared to one or more rules of an ontology rule database that correspond to the ontology topic. A check is performed to determine if a performance of the ontology extractor is acceptable.

公开(公告)号：ZA202102686B

公开(公告)日：2022-08-31

申请号：ZA202102686

申请日：2021-04-22

Applicant: IBM

Inventor： LUUS FRANCOIS PIERRE ,  KHAN NAWEED AGHMAD ,  MAKONDO NDIVHUWO ,  VOS ETIENNE EBEN ,  AKHALWAYA ISMAIL YUNUS

Abstract: Methods and systems for generating representative data. A generator is configured to create, using a learning model, one or more generated records based on a plurality of training records obtained from a sensitive database. A discriminator is trained to identify the generated records as being generated based on the training records and a privacy adversary is trained to identify a training sample as being more similar to a distribution of the generated records than a distribution of the reference records.

公开(公告)号：ZA202004652B

公开(公告)日：2021-08-25

申请号：ZA202004652

申请日：2020-07-28

Applicant: IBM

Inventor： YOUNG RICHARD A ,  GRITZMAN ASHLEY D ,  KURIEN TOBY ,  KHAN NAWEED AGHMAD ,  AKHALWAYA ISMAIL YUNUS

Abstract: One or more application forms can be hosted, which application forms are received from a service provider, the service provider having been authenticated by at least one data custodian of a set of data custodians. One or more application forms include at least form fields to be populated with information. A user selection of an application form to be automatically populated can be received, the user having been authenticated by at least one data custodian of the set of data custodians. Data request is sent to at least one data custodian of the set of data custodians for automatically populating at least some of the form fields. Received data from said at least one data custodian can be collated and used to populate one or more form fields. The populated form fields can be returned to the service provider, for instance, provided a minimum requirement is met.

公开(公告)号：ZA202103572B

公开(公告)日：2022-08-31

申请号：ZA202103572

申请日：2021-05-26

Applicant: IBM

Inventor： KHAN NAWEED AGHMAD ,  MUTAHI JULIET ,  TER-MINASSIAN LUCILE ,  LUUS FRANCOIS PIERRE ,  AKHALWAYA ISMAIL YUNUS ,  WELDEMARIAM KOMMINIST

Abstract: Methods and systems for operating a machine learning system are described. In an example, a device can receive an image and assign a set of pixels in the image as a digital representation of a livestock. The device can further train a machine learning model using the digital representation. The device can further run the machine learning model to generate prediction data relating to the livestock. The device can further generate output data relating to at least one activity among a livestock value chain. The at least one activity can correspond to a process to generate a commodity based on the livestock.

公开(公告)号：ZA202100291B

公开(公告)日：2022-02-23

申请号：ZA202100291

申请日：2021-01-15

Applicant: IBM

Inventor： AKHALWAYA ISMAIL YUNUS ,  KHAN NAWEED ,  LUUS FRANCOIS PIERRE ,  MAKONDO NDIVHUWO ,  RIEGEL RYAN ,  GRAY ALEXANDER

Abstract: Word sense disambiguation using a glossary layer embedded in a deep neural network includes receiving, by one or more processors, input sentences including a plurality of words. At least two words in the plurality of words are homonyms. The one or more processors convert the plurality of words associated with each input sentence into a first vector including possible senses for the at least two words. The first vector is then combined with a second vector including a domain-specific contextual vector associated with the at least two words. The combination of the first vector with the second vector is fed into a recurrent deep logico-neural network model to generate a third vector that includes word senses for the at least two words. A threshold is set for the third vector to generate a fourth vector including a final word sense vector for the at least two words.

公开(公告)号：ZA201904990B

公开(公告)日：2020-05-27

申请号：ZA201904990

申请日：2019-07-30

Applicant: IBM

Inventor： GRITZMAN ASHLEY D ,  AKHALWAYA ISMAIL YUNUS ,  MOODLEY CHANE SIMONE ,  LUUS FRANCOIS PIERRE ,  WELDEMARIAM KOMMINIST

公开(公告)号：AU2021271230A1

公开(公告)日：2022-10-27

申请号：AU2021271230

申请日：2021-03-18

Applicant: IBM

Inventor： LUUS FRANCOIS ,  RIEGEL RYAN ,  AKHALWAYA ISMAIL YUNUS ,  KHAN NAWEED AGHMAD ,  VOS ETIENNE ,  MAKONDO NDIVHUWO

IPC: G06N3/04

Abstract: Maximum expressivity can be received representing a ratio between maximum and minimum input weights to a neuron of a neural network implementing a weighted real-valued logic gate. Operator arity can be received associated with the neuron. Logical constraints associated with the weighted real-valued logic gate can be determined in terms of weights associated with inputs to the neuron, a threshold-of-truth, and a neuron threshold for activation. The threshold-of-truth can be determined as a parameter used in an activation function of the neuron, based on solving an activation optimization formulated based on the logical constraints, the activation optimization maximizing a product of expressivity representing a distribution width of input weights to the neuron and gradient quality for the neuron given the operator arity and the maximum expressivity. The neural network of logical neurons can be trained using the activation function at the neuron, the activation function using the determined threshold-of-truth.