This inventor holds 1 USPTO granted patent. Top assignee: Ntt Research, Inc.. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Ekdeep Singh Lubana: Inventor in Deep Learning
Introduction
Ekdeep Singh Lubana is an inventor based in Sunnyvale, California. His patent work addresses methods for training neural networks, including techniques for normalizing training data.
Latest Patents
Lubana is associated with 1 patent, titled “Systems and Methods for Normalization in Deep Learning.” The invention describes normalizing a raw data set with a group normalization layer, which divides the data into groups of a predetermined size. It also describes randomly initializing a neural network’s weights and training the network with the resulting normalized data set.
Career Highlights
Lubana works at NTT Research, Inc. His patent reflects work at the intersection of data normalization and neural network training.
Collaborations
Hidenori Tanaka is identified as Lubana’s coworker. Their shared professional context at NTT Research connects them to research and innovation in computing.
Conclusion
Ekdeep Singh Lubana’s patent focuses on a practical approach to preparing data and training neural networks, highlighting his contribution to deep learning innovation.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile