Spiking Neural Network Comparator Offset Voltage Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Spiking neural network circuits face inaccuracies in spike timing due to offset voltages in typical comparators, affecting the precision of output calculations.
Innovation Solution
A spiking neural network circuit design that includes an axon circuit, synapse circuit, and neuron circuit with a comparator that generates spike signals by comparing membrane voltages with a reference voltage, and uses input/output inverted signals to adjust voltage inputs, effectively mitigating the impact of offset voltages by swapping reference and membrane voltages during comparison operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a typical comparator is used to compare membrane voltage with reference voltage, then the comparison operation can be performed, but the spike timing becomes inaccurate due to offset voltage
Solution Approach 1:
The patent applies inversion by swapping the roles of membrane voltage and reference voltage in the comparison operation. Instead of comparing membrane voltage against reference voltage, the system compares reference voltage against membrane voltage. This inversion causes the offset voltage to affect the comparison in the opposite direction, which can be compensated for to achieve accurate spike timing despite the presence of offset voltage
2Ease of operation
If offset voltage is present in the comparator, then the comparator can operate with real-world imperfections, but the timing at which spikes are output becomes inaccurate as input voltage varies
Solution Approach 1:
The patent changes the parameters of the comparison operation by inverting which voltage is treated as the signal and which is treated as the reference. This parameter change transforms the effect of offset voltage from a source of timing error into a predictable factor that can be compensated, maintaining spike timing accuracy while allowing the comparator to operate with real-world imperfections
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This design ensures precise spike timing and output calculations by operating the comparator as if there were no offset voltage, maintaining accuracy even in the presence of offset voltages, thus improving the overall precision of the spiking neural network circuit.
Implementation Method 1
a capacitor that forms a first membrane voltage based on the first current
Implementation Method 2
the comparator includes a first input terminal and a second input terminal, receives the first membrane voltage through the first input terminal and a reference voltage through the second input terminal, generates a first spike signal based on a first comparison operation of the first membrane voltage and the reference voltage
Data Source
AI summary
Disclosed is a spiking neural network circuit, which includes an axon circuit that generates first and second input spike signals, a synapse circuit that generates a first current based on the first input spike signal and a weight and generates a second current based on the second input spike signal and the weight, a capacitor that forms a first membrane voltage based on the first current, and a neuron circuit including a comparator and that resets the first membrane voltage, and after the capacitor further forms a second membrane voltage based on the second current, and the comparator includes a first input terminal and a second input terminal, receives the first membrane voltage through the first input terminal and a reference voltage through the second input terminal, generates a first spike signal based on a first comparison operation of the first membrane voltage and the reference voltage.