18299392. LOW-LATENCY TIME-ENCODED SPIKING NEURAL NETWORK simplified abstract (International Business Machines Corporation)

LOW-LATENCY TIME-ENCODED SPIKING NEURAL NETWORK

Organization Name

International Business Machines Corporation

Inventor(s)

Giovanni Cherubini of Rueschlikon (CH)

Marcel A. Kossel of Reichenburg (CH)

LOW-LATENCY TIME-ENCODED SPIKING NEURAL NETWORK - A simplified explanation of the abstract

This abstract first appeared for US patent application 18299392 titled 'LOW-LATENCY TIME-ENCODED SPIKING NEURAL NETWORK

The abstract describes a method for executing a time-encoded spiking neural network (tSNN) using an electronic circuit that connects pairs of neurons in the network.

• The electronic circuit operates at an actual clock rate corresponding to actual time steps, allowing signaling between sender and receiver neurons through parallel channels.
• Signals sent across the parallel channels encode subcycle timing information about the timing of spikes relative to subcycle time steps.
• The electronic circuit emulates the execution of the tSNN at an effective clock rate by multiplying the actual clock rate by a latency reduction factor (LRF).

Potential Applications: - Neuromorphic computing - Artificial intelligence - Robotics - Brain-computer interfaces

Problems Solved: - Efficient execution of time-encoded spiking neural networks - Reduction of latency in neural network operations

Benefits: - Faster processing of neural network information - Improved energy efficiency in neuromorphic systems - Enhanced performance in AI applications

Commercial Applications: Title: "Next-Generation Neuromorphic Computing Systems for AI and Robotics" This technology could revolutionize the field of neuromorphic computing, leading to advancements in AI systems and robotics with faster and more energy-efficient neural network operations.

Prior Art: Researchers can explore prior studies on time-encoded spiking neural networks, electronic circuits for neural networks, and latency reduction techniques in computing.

Frequently Updated Research: Stay updated on the latest developments in neuromorphic computing, artificial intelligence, and brain-inspired computing for potential advancements in time-encoded spiking neural networks.

Questions about Time-Encoded Spiking Neural Networks: 1. How does the latency reduction factor (LRF) impact the performance of the electronic circuit in emulating the tSNN? 2. What are the key differences between traditional neural networks and time-encoded spiking neural networks in terms of processing speed and efficiency?

Original Abstract Submitted

A method of executing a time-encoded spiking neural network (tSNN) that includes configuring an electronic circuit connecting pairs of neurons of the tSNN, wherein each pair of the pairs of neurons connects a sender neuron to a receiver neuron through parallel channels, and operating the electronic circuit at an actual clock rate corresponding to actual time steps, for the electronic circuit to perform signaling over said each pair at each time step of the actual time steps by sending signals in parallel across the parallel channels. Sent signals encode subcycle timing information about a timing of spikes relative to subcycle time steps, a unit duration that corresponds to a duration of said each time step divided by a latency reduction factor (LRF), for the operated electronic circuit to emulate an execution of the tSNN at an effective clock rate corresponding to the actual clock rate multiplied by the LRF.