-
公开(公告)号：US20210250166A1
公开(公告)日：2021-08-12
申请号：US16953095
申请日：2020-11-19
Applicant: swarmin.ai
Inventor： Subash Sundaresan
Abstract: A method for sharing an incrementally trained machine learning (ML) model from an edge device to other edge devices that are associated with a peer to peer network is provided. The method includes (i) receiving event data at an edge device from among one or more edge devices of the peer to peer network upon the occurrence of an event at the edge device, (ii) incrementally training a base version of a ML model at the edge device based on the received event data, (iii) generating, a unique persistent file format of the incrementally trained ML model at the edge device, (iv) optimizing a payload associated with the unique persistent file format to include one or more parameters with associated weights changing beyond a predetermined configurable threshold and (v) encapsulating the unique persistent file format with a unique metadata.
-
公开(公告)号：US11716379B2
公开(公告)日：2023-08-01
申请号：US17113083
申请日：2020-12-06
Applicant: swarmin.ai
Inventor： Subash Sundaresan
IPC: H04L67/104 , G06N20/00 , H04L9/32
CPC classification number: H04L67/104 , G06N20/00 , H04L9/3268
Abstract: A method for concurrent training and updating a machine learning (ML) model at an edge node in a peer to peer network using a certifying node is provided. The method includes performing an incremental training of the ML model by a first edge node based on one or more data points associated with a data event. The first edge node ML transfers the incrementally trained ML model to the certifying node. While awaiting a response form the certifying node, the first edge node receives a certified ML model from the certifying node. The certified ML model originates from a second edge node. The first edge node performs an incremental training of the received certified ML model based on one or more data points by re-applying the data points associated with the event data. The first edge node transfers the incrementally trained ML model to the certifying node for certification.
-
公开(公告)号：US20210258371A1
公开(公告)日：2021-08-19
申请号：US17113083
申请日：2020-12-06
Applicant: swarmin.ai
Inventor： Subash Sundaresan
Abstract: A method for concurrent training and updating a machine learning (ML) model at an edge node in a peer to peer network using a certifying node is provided. The method includes performing an incremental training of the ML model by a first edge node based on one or more data points associated with a data event. The first edge node ML transfers the incrementally trained ML model to the certifying node. While awaiting a response form the certifying node, the first edge node receives a certified ML model from the certifying node. The certified ML model originates from a second edge node. The first edge node performs an incremental training of the received certified ML model based on one or more data points by re-applying the data points associated with the event data. The first edge node transfers the incrementally trained ML model to the certifying node for certification.
-
Patent Agency Ranking
公开(公告)号：US12033039B2
公开(公告)日：2024-07-09
申请号：US17113070
申请日：2020-12-06
Applicant: swarmin.ai
Inventor： Subash Sundaresan
IPC: G06N20/00 , H04L9/32 , H04L67/1087 , G06F18/21 , G06F18/214
CPC classification number: G06N20/00 , H04L67/1093 , G06F18/2148 , G06F18/217 , H04L9/3213
Abstract: A method and a system for maintaining network integrity for incrementally training machine learning (ML) models at edge devices is provided. The method includes registering, by a certifying node, one or more edge devices with a peer to peer network. Upon registration, an incrementally updated ML model is received from a first registered device at the certifying node. The certifying node accepts the incrementally updated ML model if a contribution of the first edge device is within a predetermined threshold, and else rejects the updated ML model if the contribution is beyond the predetermined threshold. Limiting the contribution by each edge device enables prevention of skew by any of the edge devices at the certifying node. Upon accepting the updated ML model, the certifying node certifies the updated ML model and transfers the certified ML model to one or more other edge devices in the peer to peer network.
-
公开(公告)号：US20210256421A1
公开(公告)日：2021-08-19
申请号：US17113070
申请日：2020-12-06
Applicant: swarmin.ai
Inventor： Subash Sundaresan
Abstract: A method and a system for maintaining network integrity for incrementally training machine learning (ML) models at edge devices is provided. The method includes registering, by a certifying node, one or more edge devices with a peer to peer network. Upon registration, an incrementally updated ML model is received from a first registered device at the certifying node. The certifying node accepts the incrementally updated ML model if a contribution of the first edge device is within a predetermined threshold, and else rejects the updated ML model if the contribution is beyond the predetermined threshold. Limiting the contribution by each edge device enables prevention of skew by any of the edge devices at the certifying node. Upon accepting the updated ML model, the certifying node certifies the updated ML model and transfers the certified ML model to one or more other edge devices in the peer to peer network.
-
公开(公告)号：US12088719B2
公开(公告)日：2024-09-10
申请号：US17092289
申请日：2020-11-08
Applicant: swarmin.ai
Inventor： Subash Sundaresan
CPC classification number: H04L9/3213 , G06F21/57 , G06N20/00 , G06N20/20 , H04L9/32 , H04L63/08 , G06N3/098
Abstract: A method and system for incremental training of machine learning (ML) models on edge devices, is disclosed. A base version of ML model is received by a first device of the peer to peer network of devices. The base version of the ML model is incremental trained in real-time by updating weights associated with the parameters of the ML model during a predetermined window of time. The ML model are devoid of an underlying event data used to generate the incremental version of the ML model. The updated weights associated with parameters of the incrementally trained ML model and/or the respective parameters are shared by each edge device with other edge devices. The edge devices update their respective ML models based on the received updated weights and/or parameters upon subsequent events at the edge devices and the updated version of the ML models are further incrementally trained.
-
公开(公告)号：US20210250401A1
公开(公告)日：2021-08-12
申请号：US16953132
申请日：2020-11-19
Applicant: swarmin.ai
Inventor： Subash Sundaresan
Abstract: There is provided a method of operating a certifying node to certify incremental trained machine learning (ML) models of one or more edge devices associated with a peer to peer network. The method includes (i) generating a predictive outcome value for a test data set by executing a candidate ML model against the test data set available to the certifying node; (ii) determine a measure of quality of the candidate ML model by matching the predictive outcome value of the candidate ML model with an actual outcome value of the test data set; and (iii) certify the candidate ML model by comparing the measure of quality of the candidate ML model against a threshold error value, for use in real time incremental training by the one or more edge devices of the peer to peer network.
-
公开(公告)号：US20210232981A1
公开(公告)日：2021-07-29
申请号：US17092289
申请日：2020-11-08
Applicant: swarmin.ai
Inventor： Subash Sundaresan
Abstract: A method and system for incremental training of machine learning (ML) models on edge devices, is disclosed. A base version of ML model is received by a first device of the peer to peer network of devices. The base version of the ML model is incremental trained in real-time by updating weights associated with the parameters of the ML model during a predetermined window of time. The ML model are devoid of an underlying event data used to generate the incremental version of the ML model. The updated weights associated with parameters of the incrementally trained ML model and/or the respective parameters are shared by each edge device with other edge devices. The edge devices update their respective ML models based on the received updated weights and/or parameters upon subsequent events at the edge devices and the updated version of the ML models are further incrementally trained.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.011 seconds)
