Inventor · disambiguated record
Rajiv Mathews
Also filed as: MATHEWS RAJIV
13 granted patents·19 pending applications·32 citations·filing 2008–2025
88Inventor score
Top patents by PatentIndex Score
32 records- 0191US12205575B2Mixed client-server federated learning of machine learning model(s)GOOGLE LLC·Filed 2023·Granted Jan 21, 2025·3 cites·19 claims
- 0291US11955134B2Phrase extraction for ASR modelsGOOGLE LLC·Filed 2021·Granted Apr 9, 2024·3 cites·22 claims
- 0391US11749261B2Mixed client-server federated learning of machine learning model(s)GOOGLE LLC·Filed 2021·Granted Sep 5, 2023·4 cites·20 claims
- 0488US12014739B2Using corrections, of automated assistant functions, for training of on-device machine learning modelsGOOGLE LLC·Filed 2023·Granted Jun 18, 2024·1 cites·20 claims
- 0588US11741953B2Using corrections, of automated assistant functions, for training of on-device machine learning modelsGOOGLE LLC·Filed 2019·Granted Aug 29, 2023·7 cites·18 claims
- 0679US10073874B1Updating inverted indicesGOOGLE INC·Filed 2013·Granted Sep 11, 2018·6 cites·26 claims
- 0777US2025037707A1Mixed client-server federated learning of machine learning model(s)GOOGLE LLC·Filed 2024·Application pending·0 cites
- 0875US12272360B2Using corrections, of automated assistant functions, for training of on-device machine learning modelsGOOGLE LLC·Filed 2024·Granted Apr 8, 2025·0 cites·20 claims
- 0975US8521581B2Interactive text message advertisementsBELWADI S SRIKANTH·Filed 2008·Granted Aug 27, 2013·7 cites·23 claims
- 1073US12260875B2Phrase extraction for ASR modelsGOOGLE LLC·Filed 2024·Granted Mar 25, 2025·0 cites·18 claims
- 1168US2025201262A1Phrase Extraction for ASR ModelsGOOGLE LLC·Filed 2025·Application pending·0 cites
- 1263US12223952B2Generation and utilization of pseudo-correction(s) to prevent forgetting of personalized on-device automatic speech recognition (ASR) model(s)GOOGLE LLC·Filed 2022·Granted Feb 11, 2025·0 cites·20 claims
- 1363US2025157465A1Generation and utilization of pseudo-correction(s) to prevent forgetting of personalized on-device automatic speech recognition (asr) model(s)GOOGLE LLC·Filed 2025·Application pending·0 cites
- 1462US2025149026A1Extremely fast utterances for measuring unintended memorization in automatic speech recognition modelsGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1561US10474650B1In-place updates for inverted indicesGOOGLE INC·Filed 2013·Granted Nov 12, 2019·1 cites·19 claims
- 1661US2024330767A1Co-distillation for mixing server-based and federated learningGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1761US2024330766A1Filtering for mixing server-based and federated learningGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1860US2025045627A1Utilizing elastic weight consolidation (ewc) loss term(s) to mitigate catastrophic forgetting in training machine learning model(s)GOOGLE LLC·Filed 2023·Application pending·0 cites
- 1957US2024095594A1Leveraging intermediate checkpoints to improve the performance of trained differentially private modelsGOOGLE LLC·Filed 2023·Application pending·0 cites
- 2056US2025118293A1Chain of thought reasoning for asrGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2156US2025238722A1Per-core gradient clipping in multi-core training of machine learning (ml) model(s)GOOGLE LLC·Filed 2024·Application pending·0 cites
- 2255US2023351246A1Utilizing elastic weight consolidation (ewc) loss term(s) to mitigate catastrophic forgetting in federated learning of machine learning model(s)GOOGLE LLC·Filed 2022·Application pending·0 cites
- 2355US2024249193A1Heterogeneous Federated Learning Via Multi-Directional Knowledge DistillationGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2455US2024386318A1Checkpoint averaging to mitigate and/or eliminate catastrophic forgetting of machine learning model(s) in decentralized learning thereofGOOGLE LLC·Filed 2023·Application pending·0 cites
- 2552US12505382B2Hybrid federated learning of machine learning model(s)GOOGLE LLC·Filed 2022·Granted Dec 23, 2025·0 cites·20 claims
- 2652US2024371362A1Fly parameter compression and decompression to facilitate forward and/or back propagation at clients during federated learningGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2752US2023359907A1System(s) and method(s) for jointly learning machine learning model(s) based on server data and client dataGOOGLE LLC·Filed 2022·Application pending·0 cites
- 2851US2023103911A1Leveraging Public Data in Training Neural Networks with Private Mirror DescentGOOGLE LLC·Filed 2022·Application pending·0 cites
- 2951US2024095582A1Decentralized learning of machine learning model(s) through utilization of stale updates(s) received from straggler computing device(s)GOOGLE LLC·Filed 2022·Application pending·0 cites
- 3048US12340799B2Identifying and correcting automatic speech recognition (ASR) misrecognitions in a decentralized mannerGOOGLE LLC·Filed 2022·Granted Jun 24, 2025·0 cites·20 claims
- 3147US2022383204A1Ascertaining and/or mitigating extent of effective reconstruction, of predictions, from model updates transmitted in federated learningGOOGLE LLC·Filed 2021·Application pending·0 cites
- 3240US2024194192A1Federated knowledge distillation on an encoder of a global asr model and/or an encoder of a client asr modelGOOGLE LLC·Filed 2022·Application pending·0 cites
Join the waitlist — get patent alerts
Get an alert when Rajiv Mathews files or is granted a new patent.
We store only your email — no account needed. See our privacy policy.
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →