Patents by Inventor Etienne Eben Vos
Etienne Eben Vos has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11934441Abstract: 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.Type: GrantFiled: April 29, 2020Date of Patent: March 19, 2024Assignee: International Business Machines CorporationInventors: Francois Pierre Luus, Etienne Eben Vos, Ndivhuwo Makondo, Naweed Aghmad Khan, Ismail Yunus Akhalwaya
-
Patent number: 11880015Abstract: Train a machine learning model, using an image-based knowledge graph of tropical cyclone data, for implementing a surface field modeling architecture that produces images of at least surface wind fields and surface rainfall fields from images of at least tropical cyclone tracks and pressure intensities. Generate model images of a modeled surface wind field and a modeled surface rainfall field by providing images of at least a user-generated tropical cyclone track and pressure intensity to the trained machine learning model.Type: GrantFiled: June 7, 2021Date of Patent: January 23, 2024Assignee: International Business Machines CorporationInventors: Campbell D Watson, Etienne Eben Vos, Komminist Weldemariam
-
Patent number: 11803657Abstract: 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.Type: GrantFiled: April 23, 2020Date of Patent: October 31, 2023Assignee: International Business Machines CorporationInventors: Francois Pierre Luus, Naweed Aghmad Khan, Ndivhuwo Makondo, Etienne Eben Vos, Ismail Yunus Akhalwaya
-
Publication number: 20230280495Abstract: A method, computer program, and computer system are provided for identifying bias in weather models. Data corresponding to one or more forecasts associated with a weather model is received. One or more forecast errors in the received data are identified. A forecast bias is determined from among the one or more forecast errors based on determining a presence of consistent errors in a plurality of regions associated with the received data over a period of time. The weather model is updated based on minimizing the determined forecast bias.Type: ApplicationFiled: March 7, 2022Publication date: September 7, 2023Inventors: Etienne Eben Vos, Sibusisiwe Audrey Makhanya, Zubeida Patel, Thabang Mathonsi
-
Publication number: 20220390647Abstract: Train a machine learning model, using an image-based knowledge graph of tropical cyclone data, for implementing a surface field modeling architecture that produces images of at least surface wind fields and surface rainfall fields from images of at least tropical cyclone tracks and pressure intensities. Generate model images of a modeled surface wind field and a modeled surface rainfall field by providing images of at least a user-generated tropical cyclone track and pressure intensity to the trained machine learning model.Type: ApplicationFiled: June 7, 2021Publication date: December 8, 2022Inventors: Campbell D. Watson, Etienne Eben Vos, Komminist Weldemariam
-
Patent number: 11494634Abstract: 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.Type: GrantFiled: May 13, 2020Date of Patent: November 8, 2022Assignee: International Business Machines CorporationInventors: Francois Pierre Luus, Ryan Nelson Riegel, Ismail Yunus Akhalwaya, Naweed Aghmad Khan, Etienne Eben Vos, Ndivhuwo Makondo
-
Publication number: 20220342115Abstract: A method, a computer system, and a computer program product for regionalized climate models is provided. Embodiments of the present invention may include selecting a class of a reduced order model. Embodiments of the present invention may include building a neural network in a reduced order space. Embodiments of the present invention may include recovering full state dynamics. Embodiments of the present invention may include training a model. Embodiments of the present invention may include providing an output.Type: ApplicationFiled: April 23, 2021Publication date: October 27, 2022Inventors: Etienne Eben Vos, Campbell D. Watson, Alberto Costa Nogueira Junior, Bianca Zadrozny, Komminist Weldemariam
-
Publication number: 20210357738Abstract: 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.Type: ApplicationFiled: May 13, 2020Publication date: November 18, 2021Inventors: Francois Pierre Luus, Ryan Nelson Riegel, Ismail Yunus Akhalwaya, Naweed Aghmad Khan, Etienne Eben Vos, Ndivhuwo Makondo
-
Publication number: 20210342380Abstract: 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.Type: ApplicationFiled: April 29, 2020Publication date: November 4, 2021Inventors: Francois Pierre Luus, Etienne Eben Vos, Ndivhuwo Makondo, Naweed Aghmad Khan, Ismail Yunus Akhalwaya
-
Publication number: 20210334403Abstract: 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.Type: ApplicationFiled: April 23, 2020Publication date: October 28, 2021Inventors: Francois Pierre Luus, Naweed Aghmad Khan, Ndivhuwo Makondo, Etienne Eben Vos, Ismail Yunus Akhalwaya
-
Patent number: 10903863Abstract: A first set of signal data is received. Generative machine learning models are trained based on the first set of signal data. The generative machine learning models include at least a first model trained to identify a first signal component and a second model trained to identify a second signal component. An incoming mixed signal data stream is dynamically separated into a clean signal component and a noise signal component by running the generative machine learning models.Type: GrantFiled: December 11, 2019Date of Patent: January 26, 2021Assignee: International Business Machines CorporationInventors: Francois Pierre Luus, Etienne Eben Vos, Komminist Weldemariam
-
Publication number: 20200294166Abstract: A computer-implemented method provides career options and comprising classifying, by an academic classification module, each of a plurality of academic subjects into a plurality of topics and classifying, by a career classification module, each of a plurality of career options as comprising a plurality of topics. The method comprises determining, by a grading module, for a student, a grade associated with each topic for each subject and calculating, by a prediction module, a degree of match for each career option for the student, the degree of match based on each topic which comprises the career option weighted according to the grade associated therewith.Type: ApplicationFiled: March 14, 2019Publication date: September 17, 2020Inventors: Etienne Eben Vos, Matokollo Magadla, Mathibele Willy Nchabeleng
-
Publication number: 20200177219Abstract: A first set of signal data is received. Generative machine learning models are trained based on the first set of signal data. The generative machine learning models include at least a first model trained to identify a first signal component and a second model trained to identify a second signal component. An incoming mixed signal data stream is dynamically separated into a clean signal component and a noise signal component by running the generative machine learning models.Type: ApplicationFiled: December 11, 2019Publication date: June 4, 2020Inventors: Francois Pierre Luus, Etienne Eben Vos, Komminist Weldemariam
-
Patent number: 10601454Abstract: A first set of signal data is received. Generative machine learning models are trained based on the first set of signal data. The generative machine learning models include at least a first model trained to identify a first signal component and a second model trained to identify a second signal component. An incoming mixed signal data stream is dynamically separated into a clean signal component and a noise signal component by running the generative machine learning models.Type: GrantFiled: November 30, 2018Date of Patent: March 24, 2020Assignee: International Business Machines CorporationInventors: Francois Pierre Luus, Etienne Eben Vos, Komminist Weldemariam