Cambridge, MA, United States of America

Liane Sarah Beland Bernstein

This inventor holds 2 USPTO granted patents. Top assignees: Massachusetts Institute of Technology, Ntt Research, Inc.. Active years: 2023-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Liane Sarah Beland Bernstein. Retrieved from https://idiyas.com/inventor/liane-sarah-beland-bernstein

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank

% Patents Active = 50.0

Average Co-Inventor Count = 3.0

ph-index = 1


Company Filing History:


Years Active: 2023-2026

Loading Chart...
2 patents (USPTO):Explore Patents

Title: Liane Sarah Beland Bernstein: Innovator in Optical Inference Technology

Introduction

Liane Sarah Beland Bernstein is a prominent inventor based in Cambridge, MA (US). She has made significant contributions to the field of optical inference technology, holding 2 patents that showcase her innovative approach to machine learning and deep neural networks.

Latest Patents

Her latest patents include the development of In-network Optical Inference (IOI), which provides low-latency machine learning inference by leveraging programmable switches and optical matrix multiplication. The IOI utilizes a transceiver module known as the Neuro Transceiver, equipped with an optical processor to perform linear operations, such as matrix multiplication, in the optical domain. This technology allows for the processing of inference queries at programmable packet switches within the network, significantly reducing end-to-end inference latency experienced by users.

Another notable patent is the scalable, ultra-low-latency photonic tensor processor. This processor addresses the limitations of deep neural networks (DNNs) as they grow in complexity. It can compute DNN layer outputs in a single shot, utilizing free-space optics for passive optical copying and distribution of input vectors, along with integrated optoelectronics for passive weighting and nonlinearity. An example of this processor achieved a classification accuracy of 94% on the MNIST handwritten digit dataset, demonstrating its effectiveness in near-exascale computing.

Career Highlights

Liane has worked with prestigious organizations, including the Massachusetts Institute of Technology and NTT Research, Inc. Her work has been instrumental in advancing the capabilities of optical technologies in machine learning applications.

Collaborations

Throughout her career, Liane has collaborated with notable individuals such as Dirk Robert Englund and Alexander Sludds, contributing to the development of cutting-edge technologies in her field.

Conclusion

Liane Sarah Beland Bernstein is a trailblazer in the realm of optical inference technology, with her innovative patents paving the way for advancements in machine learning and deep neural networks. Her contributions continue to influence the future of technology in significant ways.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…