Spiking Neuron Circuit With Dual Capacitive Nodes for Strong Excitation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing spiking neurons malfunction when strongly excited, leading to impaired operation and processing performance.
Innovation Solution
An electronic circuit for an artificial neuron is designed with a capacitive node and transistors configured to control discharge based on threshold conditions, utilizing inverters and NOR gates to manage membrane potential and discharge, enhancing the neuron's response to strong excitations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing spiking neurons are used, then they can generate pulse response according to excitation signals, but they malfunction when strongly excited
Solution Approach 1:
The patent divides the neuron circuit into two separate capacitive nodes: a first capacitive node for integrating excitatory inputs and a second capacitive node for controlling the discharge transistor. This segmentation allows the integration function and discharge control function to operate independently, preventing the malfunction that occurs in conventional single-node designs when strongly excited. The first node accumulates charge from excitatory signals while the second node regulates the discharge process through threshold-based control, ensuring reliable operation even under strong excitation conditions.
2Power
If the neuron integrates strong excitatory signals, then the membrane potential increases, but the discharge control becomes unstable
Solution Approach 1:
The patent introduces a second capacitive node as an intermediary between the first capacitive node (which integrates strong excitatory signals) and the discharge transistor. This intermediary node stabilizes the discharge control by providing a buffered threshold voltage that is less sensitive to fluctuations in the membrane potential. The second node's potential controls the discharge transistor gate, creating a stable control mechanism that prevents discharge instability even when the first node experiences large potential changes due to strong excitation.
Data Source
AI summary
An artificial neuron includes a first capacitive node of application of a membrane potential of the neuron. A first transistor is configured to discharge the first capacitive node. A second capacitive node is driven according to the membrane potential and delivers a potential for controlling the first transistor. A second transistor is configured to discharge the second capacitive node. The second transistor is controlled according to a potential present at the second capacitive node.