Unlocking the Power of Mirror Symmetry in Spiking Neural Networks

Introduction

In the fast-paced world of artificial intelligence and neural networks, there’s one concept that has remained at the forefront of innovation—spiking neural networks (SNNs). These biologically inspired models have the potential to mimic human brain activity more accurately than traditional AI systems. Our patented approach to identifying mirror symmetry density with delay in spiking neural networks provides a key advancement in this area, offering unprecedented insights and functionality.

Spiking neural networks are unique in that they process information in ways that closely mirror how neurons communicate in the brain—through electrical impulses or “spikes.” This approach gives them an edge when it comes to real-time decision-making and pattern recognition, which are essential in fields such as robotics, healthcare, and AI research. What our innovation does is push the boundaries of SNN capabilities by introducing the concept of mirror symmetry density with delay. Essentially, it enables more complex and precise patterns to be detected, offering an advanced level of decision-making and learning.

By identifying mirror symmetry density with delay, this technology can address some of the most persistent challenges faced by current neural network models. For instance, many AI systems struggle to recognize symmetrical patterns when there are inherent delays in information processing, something that is common in biological systems. Our approach not only solves this problem but also enhances the network’s ability to learn from and adapt to such situations, improving overall performance in complex environments.

Imagine applying this innovation in autonomous systems—whether it’s a robot navigating an unfamiliar terrain or an autonomous vehicle processing multiple signals simultaneously. The ability to recognize delayed symmetrical patterns could drastically enhance real-time decision-making, making these systems more reliable and efficient. Similarly, this technology can transform neural network-based diagnostics in healthcare by improving how medical devices analyze complex neural patterns, potentially leading to breakthroughs in conditions like epilepsy or Parkinson’s.

Licensing this technology opens the door to cutting-edge applications in robotics, AI, and neuroscience. By integrating this system, your organization can leverage the power of biologically inspired learning models, leading to more accurate, adaptive, and intelligent systems across industries.

Please see terms and conditions

Abstract
Claims

The ability to rapidly identify symmetry and anti-symmetry is an essential attribute of intelligence. Symmetry perception is a central process in human vision and may be key to human 3D visualization. While previous work in understanding neuron symmetry perception has concentrated on the neuron as an integrator, the invention provides the coincidence detecting property of the spiking neuron can be used to reveal symmetry density in spatial data. A synchronized symmetry-identifying spiking artificial neural network enables layering and feedback in the network. The network of the invention can identify symmetry density between sets of data and present a digital logic implementation demonstrating an 8×8 leaky-integrate-and-fire symmetry detector in a field-programmable gate array. The efficiency of spiking neural networks can be harnessed to rapidly identify symmetry in spatial data with applications in image processing, 3D computer vision, and robotics.

The invention claimed is:

1. A symmetry detector to detect symmetry of input data, said symmetry detector comprising:

a plurality of input nodes, each input node receiving a discrete data point of the input data, each input node representing a data point at a fixed position in an N dimensional metric space, and having a spike producer configured to produce spiked data as a threshold of the input data and delay devices configured to delay the produced spiked data by a fixed time constant representing distance in the metric space and provide delayed output data; and

a plurality of output nodes, each output node connected to one or more of the plurality of input nodes, each output node representing output data at a fixed position also in the same N dimensional metric space as the input nodes, receiving the delayed output data, from each of the connected one or more plurality of input nodes, where each delay is constant and set proportionally to the distance in the metric space between the input node and the output node, and each output node having a coincidence detector configured to detect symmetry based on delayed output data that is spiked.

2. The symmetry detector of claim 1, said plurality of input nodes and said plurality of output nodes each comprising a neuron.

3. The symmetry detector of claim 1, said coincidence detector comprising a plurality of multipliers each configured to multiply the delayed output data from each of the connected one or more said plurality of input nodes by a corresponding weight value, an accumulator configured to receive and accumulate the multiplied delayed output data and a threshold detector configured to detect a threshold number of spiked data in the accumulated multiplied delayed output data.

4. The symmetry detector of claim 1, wherein the threshold number represents symmetry of input data.

5. The symmetry detector of claim 1, said spike producer comprising a multiplier configured to multiply the input data by a corresponding weight value, an accumulator configured to receive the multiplied input, a threshold detector configured to detect spiked data in the input data and provide the detected spiked input data.

6. The symmetry detector of claim 5, said accumulator having leak configured to adjust the sensitivity of the output node to detecting symmetry.

7. The symmetry detector of claim 1, said delay device comprising a set of clocks, or a delay counter, or a routing delay.

8. The symmetry detector of claim 1, wherein the delay is proportional to a distance between each respective input node and each respective output node, in the data space.

9. A symmetry detector to detect symmetry of input data, said symmetry detector comprising:

a plurality of input nodes, each input node receiving a discrete data point of the input data, each input node representing a data point at a fixed position in an N dimensional metric space, and having a spike producer configured to produce spiked data by a fixed time constant representing distance in the metric space as a threshold of the input data; and

a plurality of output nodes, each output node connected to one or more of the plurality of input nodes, each output node representing output data at a fixed position also in the same N dimensional metric space as the input nodes, receiving the input node output data from each of the one or more connected plurality of input nodes, each output node having a delay device delaying the input node output data to provide a delayed input node output data, where each delay is constant and set proportionally to the distance in the metric space between the input node and the output node, and each output node having a coincidence detector configured to detect a threshold number of spikes in the delayed input node output data in a given period of time.

10. The symmetry detector of claim 9, said plurality of input nodes and said plurality of output nodes each comprising a neuron.

11. The symmetry detector of claim 9, said coincidence detector comprising an accumulator configured to receive and accumulate the delayed input node output data and a threshold detector coupled to the accumulator configured to identify the threshold number of spikes.

12. The symmetry detector of claim 11, said accumulator having leak configured to adjust the sensitivity of the output node to detecting symmetry.

13. The symmetry detector of claim 9, wherein the threshold number represents symmetry of input data.

14. The symmetry detector of claim 9, said delay device comprising a set of clocks, or a delay counter, or a routing delay.

15. The symmetry detector of claim 1, the spiked data comprising a temporal pulse.

Title

Identifying mirror symmetry density with delay in spiking neural networks

Inventor(s)

Jonathan K. George, Volker J. Sorger

Assignee(s)

George Washington University

Patent #

11599776

Patent Date

March 7, 2023