公开(公告)号：US12136078B2

公开(公告)日：2024-11-05

申请号：US17826463

申请日：2022-05-27

Applicant: BANK OF AMERICA CORPORATION

Inventor： Craig D. Widmann ,  Eren Kursun

IPC: G06Q20/22 ,  G06F16/23 ,  G06Q20/02 ,  G06Q30/06

Abstract: A system for event-based peer-to-peer resource transfers. The system may include a controller configured for tracking and confirming resource transfers, the controller being further configured to: generate a resource transfer for transferring a resource from a first user device to a second user device, where the resource transfer includes a conditional event for triggering a transfer of the resource, and where the conditional event is accepted by the first user device and the second user device; receive the resource from the first user device, where the resource is held separate from the first user device and the second user device; determine that the conditional event has been executed by at least one of the first user device and the second user device; and based on the determining that the conditional event has been executed, trigger the transfer of the resource to the second user device.

公开(公告)号：US20240354576A1

公开(公告)日：2024-10-24

申请号：US18759369

申请日：2024-06-28

Applicant: BANK OF AMERICA CORPORATION

Inventor： Eren Kursun

IPC: G06N3/082 ,  G06F17/11 ,  G06F18/214 ,  G06N3/044 ,  G06N3/045

CPC classification number: G06N3/082 ,  G06F17/11 ,  G06F18/214 ,  G06N3/044 ,  G06N3/045

Abstract: The present disclosure is directed to a novel system for a self-constructing deep neural network. The system may comprise a hybrid logic library which contains the building structures needed to construct the neural network, which may include both traditional logic and memory structures as well as learning structures. In constructing the neural network from library structures, the system may use an algorithm to iteratively improve the performance of the neural network. In this way, the system may provide a way to generate complex neural networks that become increasingly optimized over time.

公开(公告)号：US20230316076A1

公开(公告)日：2023-10-05

申请号：US18207861

申请日：2023-06-09

Applicant: Bank of America Corporation

Inventor： Ronnie J. Morris ,  Dana M. Pusey-Conlin ,  Lorraine C. Edkin ,  Scott A. Sims ,  Joel Filliben ,  Margaret A. Payne ,  Craig Douglas Widmann ,  Eren Kursun

IPC: G06N3/08 ,  G06N3/04 ,  G06F16/26 ,  G06F16/28 ,  G06F16/22

CPC classification number: G06N3/08 ,  G06N3/04 ,  G06F16/26 ,  G06F16/288 ,  G06F16/2291

Abstract: Machine learning models, semantic networks, adaptive systems, artificial neural networks, convolutional neural networks, and other forms of knowledge processing systems are disclosed. An ensemble machine learning system is coupled to a graph module storing a graph structure, wherein a collection of entities and the relationships between those entities forms nodes and connection arcs between the various nodes. A hotfile module and hotfile propagation engine coordinate with the graph module or may be subsumed within the graph module, and implement the various hot file functionality generated by the machine learning systems.

公开(公告)号：US11669713B2

公开(公告)日：2023-06-06

申请号：US16209372

申请日：2018-12-04

Applicant: Bank of America Corporation

Inventor： Eren Kursun

IPC: G06N3/02 ,  G06F9/445

CPC classification number: G06N3/02 ,  G06F9/44505

Abstract: The present disclosure is directed to a novel system for performing online reconfiguration of a neural network. Once a neural network has been implemented into a production environment, the system may use underlying construction logic to perform an in-situ reconfiguration of neural network elements while the neural network is live. The system may accomplish the reconfiguration by modifying the architecture of the neural network and/or performing adversarial training and/or retraining. In this way, the system may provide a way increase the performance of the neural network over time along one or more performance parameters or metrics.

公开(公告)号：US11526725B2

公开(公告)日：2022-12-13

申请号：US16706529

申请日：2019-12-06

Applicant: BANK OF AMERICA CORPORATION

Inventor： Eren Kursun

IPC: G06N3/04 ,  G06F21/31 ,  G06F16/904 ,  G06K9/62 ,  G06N3/08

Abstract: A system for attention-based layered neural network classification is provided. The system comprises: a sequence of layered neural networks; and a controller configured for controlling data routed through the sequence of layered neural networks, the controller configured to: receive interaction data comprising data features, wherein the data features are distinct characteristics of the interaction data; input data features into the sequence of layered neural networks, wherein each sequential layer of the sequence of layered neural networks comprises a heightened rigor level for at least one of the data features; calculate a relevance score output for at least one of the data features at each layer of the sequence of layered neural networks; and integrate the relevance score output from each layer of the sequence of layered neural networks to generate a total relevance score output.

公开(公告)号：US11468361B2

公开(公告)日：2022-10-11

申请号：US16422384

申请日：2019-05-24

Applicant: BANK OF AMERICA CORPORATION

Inventor： Eren Kursun ,  Hylton N. van Zyl

IPC: G06N20/10 ,  G06N20/00 ,  G06F21/57 ,  H04L9/40

Abstract: An artificial intelligence system and method for real-time event trend analysis are provided for a population of machine learning models configured to monitor a real-time data stream. A controller is configured for analyzing the population of machine learning models and determining data trends in response to changes in the real-time data stream; receiving a collective output from the population of machine learning models, wherein the output comprises an analysis of the real-time data stream; extracting an event horizon data trend based on the collective output, the event horizon data trend comprising a determined upcoming data variation in the real-time data stream; and continuously reconfiguring the population of machine learning models based on the collective output and the event horizon data trend.

公开(公告)号：US20220292480A1

公开(公告)日：2022-09-15

申请号：US17826463

申请日：2022-05-27

Applicant: BANK OF AMERICA CORPORATION

Inventor： Craig D. Widmann ,  Eren Kursun

IPC: G06Q20/22 ,  G06Q20/02 ,  G06F16/23

Abstract: A system for event-based peer-to-peer resource transfers. The system may include a controller configured for tracking and confirming resource transfers, the controller being further configured to: generate a resource transfer for transferring a resource from a first user device to a second user device, where the resource transfer includes a conditional event for triggering a transfer of the resource, and where the conditional event is accepted by the first user device and the second user device; receive the resource from the first user device, where the resource is held separate from the first user device and the second user device; determine that the conditional event has been executed by at least one of the first user device and the second user device; and based on the determining that the conditional event has been executed, trigger the transfer of the resource to the second user device.

公开(公告)号：US11354602B2

公开(公告)日：2022-06-07

申请号：US16431019

申请日：2019-06-04

Applicant: BANK OF AMERICA CORPORATION

Inventor： Eren Kursun

IPC: H04L29/06 ,  G06F21/55 ,  G06N20/20 ,  H04L9/40 ,  G06F21/56 ,  H04L61/4511 ,  G06N20/00

Abstract: Embodiments of the present invention provide a system and methods to mitigate poisoning attacks within machine learning systems. The invention includes an improved data analysis approach to train an ensemble of machine learning models to analyze received data and label the data in a non-binary fashion to indicate likelihood that certain data has been injected abnormally and should not be used for training purposes. The resulting dataset from the ensemble is assessed to determine convergence of model labeling and to detect outlier data labeling among models in the ensemble. Confidence scores for clustered interaction data may be performed on varied sets of training data populations and using a number of models. Output from the various training/model mixes are fed to a machine learning model to compare ensemble accuracy between different model sets and select the most accurate ensemble combination.

公开(公告)号：US11347845B2

公开(公告)日：2022-05-31

申请号：US16431046

申请日：2019-06-04

Applicant: BANK OF AMERICA CORPORATION

Inventor： Eren Kursun

IPC: G06F21/55 ,  G06N20/00

Abstract: Embodiments of the present invention provide a system and methods to prevent poisoning attacks in machine learning systems in real time. The invention includes methods for blocking the injection of abnormal data into training data sets used to train machine learning models for the identification of malfeasant activity by blocking certain data from entering the machine learning training dataset in real time, blocking certain interactions from being completed in real time, or placing holds on certain resources or users according to patterns detected by the ensemble of machine learning models. Various thresholds may be set manually or identified through the machine learning algorithm in order to determine which interactions or users should be blocked.

公开(公告)号：US11341485B2

公开(公告)日：2022-05-24

申请号：US16532895

申请日：2019-08-06

Applicant: Bank of America Corporation

Inventor： Eren Kursun

IPC: G06Q20/36 ,  G06Q20/40 ,  G06N20/00

Abstract: Systems, computer program products, and methods are described herein for machine learning based system for authorization of autonomous resource transfers between distributed IoT components. The present invention is configured to receive, from a first autonomous IoT device, a transaction authorization request to execute a transaction with a second autonomous IoT device; receive information associated with the first autonomous IoT device, information associated with the second autonomous IoT device, and information associated with the transaction; initiate an execution of one or more machine learning algorithms; determine that the first autonomous IoT device is authorized to execute the transaction with the second autonomous IoT device; transmit a transaction authorization to the first autonomous IoT device to execute the transaction; and receive, from the first autonomous IoT device, an indication that the transaction has been executed.