System and method for max-margin adversarial training
31 Jan 23
A system for generating an adversarial example in respect of a neural network, the adversarial example generated to improve a margin defined as a distance from a data example to a neural network decision boundary.
Weiguang Ding, Yash Sharma, Yik Chau Lui, Ruitong Huang
Filed: 25 Oct 19
Correcting bias in supervised machine learning data
31 Jan 23
An electronic device and method of correcting bias for supervised machine learning data is provided.
Jaspreet Sahota, Janahan Ramanan, Yuanqiao Wu, Yik Chau Lui
Filed: 13 Jun 19
Systems and methods for learning user representations for open vocabulary data sets
31 Jan 23
Systems and methods adapted for training a machine learning model to predict data labels are described.
Thibaut Durand, Gregory Mori
Filed: 21 Mar 20
System and Method for Duplicating an Application State
26 Jan 23
A computer system and computer-implemented method for duplicating an application state are provided, the method including: recording one or more point-in-time characteristics generated by prior user inputs at one or more user interface elements, the one or more point-in-time characteristics associated with a first application state of a first application instance; transferring the one or more point-in-time characteristics to the provisioned memory resources for generating the second application state; generating a second application instance based on the one or more point-in-time characteristics; configuring the second application state based on the one or more point-in-time characteristics to duplicate the first application state of the first application instance; and storing the prior user inputs in a journal, wherein the journal is configured to enable reproduction of a state of a plurality of modified states of the first application instance.
Philip IANNACCONE, Walter Michael PITIO, James BROWN
Filed: 3 Oct 22
System and Method for Composite Cryptographic Transactions
26 Jan 23
A composite cryptographic data structure is described, and corresponding methods, systems, and computer readable media.
Karim Talal HAMASNI, Stefan MUELLER, Atilla Murat FIRAT, Matthew Thomas PESKETT
Filed: 7 Oct 22
Robust pruned neural networks via adversarial training
24 Jan 23
Systems, methods, and computer readable media are described to train a compressed neural network with high robustness.
Luyu Wang, Weiguang Ding, Ruitong Huang, Yanshuai Cao, Yik Chau Lui
Filed: 7 Feb 19
Machine natural language processing for summarization and sentiment analysis
24 Jan 23
A virtual agent can implement a “chatbot” to provide output based on predictive/prescriptive models for incidents.
Yixian Cai, Amir Ghaderi, Ankit Khirwadkar, Chetana Chavda, Pei Hu
Filed: 10 May 19
System and method for machine learning architecture for enterprise capitalization
17 Jan 23
Systems and methods are described in relation to specific technical improvements adapted for machine learning architectures that conduct classification on numerical and/or unstructured data.
Hieu Quoc Nguyen, Morris Jamieson Chen, Kirtan Purohit, Diana-Elena Oprea
Filed: 14 Aug 20
Method and device for conducting measurements for an N-dimensional data structure
10 Jan 23
A method for acquiring measurements for a data structure corresponding to an array of variable includes: selecting a subset of elements from the data structure; measuring a sampled value for each of the selected subset of elements; storing each of the sampled values in a K-nearest neighbour (KNN) database and labelling the sampled value as certain; generating a predicted value data structure where each predicted element is generated as the value of its nearest neighbor based on the values stored in the KNN database; for each predicted element: retrieve the predicted element's X nearest neighbours for the sampled value in the KNN database, and when a value of the X nearest neighbours is the same as the predicted element, the predicted element is labelled as certain, otherwise the predicted element is labelled the values as uncertain; and repeating until all elements are labelled as certain.
Weiguang Ding, Ruitong Huang, Luyu Wang, Yanshuai Cao
Filed: 31 Oct 18
System and method for detecting data drift
3 Jan 23
Data drift or dataset shift is detected between training dataset and test dataset by training a scoring function using a pooled dataset, the pooled dataset including a union of the training dataset and the test dataset; obtaining an outlier score for each instance in the training dataset and the test dataset based at least in part on the scoring function; assigning a weight to each outlier score based at least in part on training contamination rates; determining a test statistic based at least in part on the outlier scores and the weights; determining a null distribution of no dataset shift for the test statistic; determining a threshold in the null distribution; and when the test statistic is greater than or equal to the threshold, identifying dataset shift between the training dataset and the test dataset.
Vathy M. Kamulete
Filed: 26 Jun 20
Systems and methods for secure tokenized credentials
27 Dec 22
Systems, devices, methods, and computer readable media are provided in various embodiments having regard to authentication using secure tokens, in accordance with various embodiments.
Edison U. Ortiz, Mohammad Abuzar Shaikh, Margaret Inez Salter, Sarah Rachel Waigh Yean Wilkinson, Arya Pourtabatabaie, Iustina-Miruna Vintila
Filed: 24 Jul 19
Systems and Methods for Dynamic Passphrases
22 Dec 22
A technical validation mechanism is described that includes the use of facial feature recognition and tokenization technology operating in combination with machine learning models can be used such that specific facial or auditory characteristics of how an originating script is effectuated can be used to train the machine learning models, which can then be used to validate a video or a particular dynamically generated passphrase by comparing overlapping phonemes or phoneme transitions between the originating script and the dynamically generated passphrase.
Edison U. ORTIZ, Mohammad Abuzar SHAIKH, Margaret Inez SALTER, Sarah Rachel Waigh Yean WILKINSON, Arya POURTABATABAIE, Iustina-Miruna VINTILA, Steven FERNANDES, Sumit Kumar JHA
Filed: 29 Aug 22
System and Method for Risk Sensitive Reinforcement Learning Architecture
22 Dec 22
A computer-implemented system and method for training an auomated agent are disclosed.
Pablo Francisco HERNANDEZ-LEAL, Yue GAO, Yik Chau LUI
Filed: 10 Jun 22
System and method for monitoring machine learning models
20 Dec 22
Systems and methods are provided to monitor performance of a machine learning model, the method may include steps of: receiving or storing one or more model data sets representative of the machine learning model, wherein the machine learning model has being trained with a first set of training data; analyzing the first set of training data based on one or more performance parameters for the machine learning model, to generate one or more performance data sets; and process the one or more performance data sets to determine one or more values representing a performance of the machine learning model.
Leandro Axel Guelman
Filed: 12 Mar 19
Method for Anomaly Detection In Clustered Data Structures
15 Dec 22
A method for generating visual representations of financial interests includes: receiving an input data set including one or more data structures storing data fields and data values representative of financial interests; extracting, from the input data, one or more extracted features from the funds, the extracted features collectively indicative of a distance between different funds; generating one or more clusters of funds, based on the extracted features of the funds; determining, based on identified differences between one or more funds relative to at least one other fund in a corresponding cluster of funds, one or more fund anomalies based on the one or more extracted features; generating one or more adjustment recommendations based on the one or more fund anomalies, the one or more adjustment recommendations representing control instruction sets for automatically modifying characteristics of the corresponding fund.
Morteza MASHAYEKHI, Iman REZAEIAN, Jonathan Albert North ANDERS
Filed: 27 Jun 22
System and Method for Multi-user Session for Coordinated Electronic Transactions
15 Dec 22
Systems, methods, and computer readable media are directed in various embodiments for providing multiuser sessions for coordinated electronic transactions.
Arnold BADAL-BADALIAN, Edison U. ORTIZ, William Kwok Hung CHEUNG, Seung Bong BAEK, Ravi KHANDAVILLI
Filed: 14 Jun 22
System and Method for Location-based Token Transaction Processing
8 Dec 22
Systems, methods, and machine-executable data structures for the processing of data for the secure creation, administration, manipulation, processing, and storage of electronic data useful in the processing of electronic payment transactions.
Edison U. ORTIZ, Arnold BADAL-BADALIAN, Ambica Pawan KHANDAVILLI, Rasha KHAYAT, Iustina-Miruna VINTILA, Nikhil Singh SHEKHAWAT
Filed: 6 Jun 22
System and method for machine learning architecture with adversarial attack defense
6 Dec 22
A platform for training deep neural networks using push-to-corner preprocessing and adversarial training.
Weiguang Ding, Luyu Wang, Ruitong Huang, Xiaomeng Jin, Kry Yik Chau Lui
Filed: 17 May 19
System and method for machine learning architecture for dynamic market stress platform
6 Dec 22
Systems and methods for responsive stress testing that involve back-end machine learning models that produce enterprise market risk calculations and a front-end interface with graphical elements to visually interact with the machine learning models.
Vincent Lok Man Chiu, Sahejpreet Kaur Johal, Roman Nikolas Heit, Asic Qian Chen, Jan Valentine Varsava
Filed: 14 Aug 20
System and Method for Adversarial Vulnerability Testing of Machine Learning Models
1 Dec 22
A system and method for adversarial vulnerability testing of machine learning models is proposed that receives as an input, a representation of a non-differentiable machine learning model, transforms the input model into a smoothed model and conducts an adversarial search against the smoothed model to generate an output data value representative of a potential vulnerability to adversarial examples.
Giuseppe Marcello Antonio CASTIGLIONE, Weiguang DING, Sayedmasoud HASHEMI AMROABADI, Ga WU, Christopher Côté SRINIVASA
Filed: 20 May 22