Spike Neural Network Circuit Radiation Source Leakage Current
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Spike neural network circuits face arithmetic errors due to increasing leakage current in transistors as the number of transistors increases, affecting the accuracy of processing spike signals.
Innovation Solution
Incorporating a radiation source attached to the substrate of the synapse circuit to increase the threshold voltages of transistors, thereby reducing leakage current and minimizing computation errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the number of transistors is increased to process more information, then the processing capability is improved, but the leakage current increases causing arithmetic errors
Solution Approach 1:
The patent applies parameter changes by modifying the threshold voltage parameter of the transistors. Specifically, it uses ion implantation to change the threshold voltage from a first value to a second value, thereby reducing leakage current while maintaining the increased transistor count for higher processing capability
Solution Approach 2:
The patent replaces conventional electrical control methods with a physical ion implantation process. Instead of using electrical fields or control circuits to manage leakage current, it employs ion beams to physically modify the transistor characteristics, achieving more effective leakage current reduction
2Reliability
If the threshold voltage is increased to reduce leakage current, then the reliability is improved, but the processing capability may be affected
Solution Approach 1:
The patent carefully controls the threshold voltage parameter change through ion implantation. By adjusting implantation conditions (ion type, energy, dose), it achieves the optimal balance where threshold voltage increases sufficiently to reduce leakage current while maintaining processing capability
Solution Approach 2:
The patent applies local quality by selectively implanting ions at specific locations and depths within the transistor structure. Different regions of the transistor receive different ion implantation treatments, allowing localized optimization of threshold voltage without uniformly degrading processing capability
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
The introduction of a radiation source effectively reduces leakage current in transistors, enhancing the accuracy of spike signal processing and reducing computation errors in spike neural network circuits.
Implementation Method 1
a radiation source attached to a substrate on which the synapse is formed, configured to output radiation particles to the synapse
Data Source
AI summary
Provided is a spike neural network circuit. The spike neural network circuit includes an axon configured to generate an input spike signal, a synapse including a first transistor for outputting a current according to a weight and a second transistor connected to the first transistor and outputting the current according to an input spike signal, a neuron configured to compare a value according to the current output from the synapse with a reference value and generate an output spike signal based on a comparison result, and a radiation source attached to a substrate on which the synapse is formed, configured to output radiation particles to the synapse, and configured to increase magnitudes of threshold voltages of the first and second transistors of the synapse.