Inventor profile of:

Ehsan Amid

City:

Mountain View, California

Country:

United States

Published Applications:

15

Last publication date:

2025-06-19

Top Assignees for applications by Ehsan Amid

The entities that hold a legal rights for patent applications filed by inventor Amid Ehsan:

Recent patent applications by Amid Ehsan

Ehsan Amid from Mountain View, US has applied for patents for these inventions. The list has both pending applications and granted patents:

#1 | 2025-06-19
US20250201262A1
Physics

Phrase Extraction for ASR Models

#2 | 2025-06-19
US20250200343A1
Physics

NEURAL NETWORKS WITH PIECEWISE LINEAR ACTIVATION FUNCTIONS

#3 | 2025-05-15
US20250156716A1
Physics

TRAINING NEURAL NETWORKS USING LAYERWISE FISHER APPROXIMATIONS

#4 | 2025-01-02
US20250005453A1
Physics

Knowledge Distillation Via Learning to Predict Principal Components Coefficients

#5 | 2024-07-25
US20240249193A1
Physics

Heterogeneous Federated Learning Via Multi-Directional Knowledge Distillation

#6 | 2024-07-11
US20240233707A9
Physics

Knowledge Distillation with Domain Mismatch For Speech Recognition

#7 | 2024-07-04
US20240221772A1
Physics

Phrase extraction for ASR models

#8 | 2024-06-13
US20240194192A1
Physics

FEDERATED KNOWLEDGE DISTILLATION ON AN ENCODER OF A GLOBAL ASR MODEL AND/OR AN ENCODER OF A CLIENT ASR MODEL

#9 | 2024-04-25
US20240135918A1
Physics

Knowledge Distillation with Domain Mismatch For Speech Recognition

#10 | 2024-03-21
US20240095582A1
Physics

DECENTRALIZED LEARNING OF MACHINE LEARNING MODEL(S) THROUGH UTILIZATION OF STALE UPDATES(S) RECEIVED FROM STRAGGLER COMPUTING DEVICE(S)

#11 | 2024-02-29
US20240070530A1
Physics

HYBRID FEDERATED LEARNING OF MACHINE LEARNING MODEL(S)

#12 | 2023-06-08
US20230178094A1
Physics

Phrase extraction for ASR models

#13 | 2023-04-06
US20230103911A1
Physics

Leveraging Public Data in Training Neural Networks with Private Mirror Descent

#14 | 2023-02-09
US20230044078A1
Physics

Unified Sample Reweighting Framework for Learning with Noisy Data and for Learning Difficult Examples or Groups

#15 | 2022-08-11
US20220253713A1
Physics

TRAINING NEURAL NETWORKS USING LAYER-WISE LOSSES

InventorID:

5489291 ⎘