Patents

Patents listed here reflect only technologies patented from FY 2018-present. To view all of NIST's patented technologies, visit the NIST pages on the Federal Laboratory Consortium website.

Displaying 1 - 4 of 4

The figure illustrates a system for parameter multiplexed gradient descent in accordance with embodiments of the present invention.

System And Method For Parameter Multiplexed Gradient Descent

NIST Inventors

Adam McCaughan , Sonia Buckley and Andrew Dienstfrey

Parameter multiplexed gradient descent (PMGD) is a machine learning training method designed to easily train emergent non-volatile memory and neuromorphic hardware platforms.

Diagram showing the circuit for resetting the Spectral Power Distribution (SPD) after the Light Emitting Diode (LED) has emitted a photonic pulse.

Superconducting Opto-Electronic Transmitter Circuit

NIST Inventors

Sonia Buckley , Adam McCaughan and Jeff Shainline

This invention describes a family of circuits that receive an input current or voltage pulse when a superconducting element has been driven above threshold, producing an amplified current or voltage pulse to drive a light source, and reset to the resting state after light has been generated.

Thermal Impedance Amplifier

NIST Inventors

Adam McCaughan , Varun Verma and Sonia Buckley

A thermal impedance amplifier includes: a resistive layer including: a resistance member; a first electrode in electrical communication with the resistance member; and a second electrode in electrical communication with the resistance member; a switch layer opposing the resistive layer and including

Neuromimetic Circuit

NIST Inventors

Jeff Shainline and Sonia Buckley

Optoelectronic neural networks comprise a system of interconnected processing units (neurons) interconnected by integrated photonic waveguides. The processing units receive photonic signals from other units. Each unit sums the received signals on a waveguide-integrated photon detector, and when the

Search Patents by Sonia Buckley