Device and method for random walk simulation
| DWPI Title: Method for simulating random walk in spiking neuromorphic hardware, involves receiving number of spiking inputs from number of upstream mesh nodes by buffer count neuron in mesh node, and sending counter spiking outputs to selected downstream mesh nodes by probability neuron |
| Abstract: A method for simulating a random walk using spiking neuromorphic hardware is provided. The method comprises receiving, by a buffer count neuron, spiking inputs from upstream mesh nodes, wherein the inputs include information packets comprising information associated with a simulation of a random walk process. A buffer generator neuron generates spikes until the buffer count reaches a first predefined threshold, after which it sends buffer spiking outputs to a spike count neuron. The spike count neuron counts the buffer spiking outputs, and a spike generator neuron generates spikes until the spike count neuron reaches a second specified threshold. The spike generator neuron then sends counter spiking outputs to a probability neuron, which selects downstream mesh nodes to receive the counter spiking outputs, wherein the spiking outputs include updated information packets. The probability neuron then sends the spiking outputs to the selected downstream nodes. |
| Use: Method for simulating random walk in a spiking neuromorphic hardware. |
| Advantage: The method enables reducing electrical power consumption by a computer simulating a large number of random walkers, thus reducing heat output, avoiding to damage equipment, and improving equipment efficiency, and hence avoiding slow computations, and preventing waste of cooling power and direct electrical power required to operate the computer. |
| Novelty: The method (400) involves receiving (402) a number of spiking inputs from a number of upstream mesh nodes by a buffer count neuron in a mesh node. First number of spikes is generated (404) until the buffer count neuron reaches first predefined threshold value by a buffer generator neuron in the mesh node in response to the spiking inputs. A number of buffer spiking outputs is sent (406) to a spike count neuron in the mesh node upon reaching the first predefined threshold value by the buffer generator neuron. The buffer spiking outputs are counted from the buffer generator neuron by the spike count neuron. Second number of spikes is generated (408) until the spike count neuron reaches second predefined threshold value by a spike generator neuron in the mesh node in response to the buffer spiking outputs. A number of counter spiking outputs is sent (410) to a probability neuron in the mesh node upon reaching the second predefined threshold value by the spike generator neuron. |
| Filed: 3/12/2021 |
| Application Number: US17200003A |
| Tech ID: SD 15346.0 |
| This invention was made with Government support under Contract No. DE-NA0003525 awarded by the United States Department of Energy/National Nuclear Security Administration. The Government has certain rights in the invention. |
| Data from Derwent World Patents Index, provided by Clarivate All rights reserved. Republication or redistribution of Clarivate content, including by framing or similar means, is prohibited without the prior written consent of Clarivate. Clarivate and its logo, as well as all other trademarks used herein are trademarks of their respective owners and used under license. |