Crossbar Code Comparator With Nonpolar Dynamic Switching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital circuits for calculating Hamming distance are inefficient due to high power consumption and require analog-to-digital conversion for analog input signals, especially when comparing strings or words involving analog inputs.
Innovation Solution
A crossbar array-based code comparator using nonpolar dynamical two-terminal devices that switch automatically from an ON state to an OFF state upon removal of electrical bias, eliminating the need for digital conversion and reducing energy consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If digital circuits are used to calculate Hamming distance, then bit-wise comparison can be performed, but power consumption increases proportionally with circuit capacitance and signal transitions
Solution Approach 1:
The patent replaces traditional digital electronic circuits with a neural network-based system that processes analog signals continuously. This substitution eliminates the need for discrete digital switching operations, thereby reducing power consumption while maintaining comparison functionality through analog voltage representations of binary data
Solution Approach 2:
The neural network architecture provides multi-functionality by performing both analog-to-digital conversion and Hamming distance calculation within a unified system. The same neural network can process different input formats and perform various comparison operations, reducing the need for separate dedicated circuits and lowering overall power consumption
2Adaptability or versatility
If analog input signals are converted to digital signals via ADC, then digital processing can be performed, but the process becomes more complex and energy-consuming
Solution Approach 1:
The patent merges the analog-to-digital conversion function with the Hamming distance calculation function into a single neural network processing stage. The neural network directly accepts analog voltage inputs representing binary data and performs comparison operations in the analog domain, eliminating the need for separate ADC circuits and reducing overall system complexity
Solution Approach 2:
The patent substitutes traditional ADC hardware with a neural network-based analog processing system. The neural network performs threshold-based decision-making and comparison operations directly on analog signals, replacing the need for discrete ADC components and simplifying the overall circuit architecture
3Ease of operation
If traditional switching devices are used, then circuit operation can be controlled, but switching speed and reset time limit processing efficiency
Solution Approach 1:
The patent employs dynamic neural network nodes that continuously adapt their states based on input signals rather than relying on discrete switching events. The analog voltages in the neural network can change continuously and rapidly in response to input changes, enabling faster processing speeds compared to traditional switching devices that require explicit reset and re-trigger cycles
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
Enhances switching speed and accuracy by automatically resetting devices, reducing energy overhead, and allowing for direct comparison of analog signals without digital conversion, while providing noise-tolerant threshold switching.
Implementation Method 1
a nonpolar volatile two-terminal device formed within a plurality of cross-point devices. Each cross-point device in the plurality of cross-point devices is located at a cross-point between a row in the plurality of row wires and a column in the plurality of column wires; the nonpolar volatile two-terminal device is configured to automatically revert from an ON state to an OFF state, in response to a removal of an electrical bias or signal applied on the nonpolar volatile two-terminal device
Data Source
AI summary
Code comparators with nonpolar dynamical switches are provided. An example apparatus comprises: a plurality of row wires; a plurality of column wires; one or more cross-point devices, and a nonpolar volatile two-terminal device formed within a plurality of cross-point devices. Each cross-point device in the plurality of cross-point devices is located at a cross-point between a row in the plurality of row wires and a column in the plurality of column wires; the nonpolar volatile two-terminal device is configured to automatically revert from an ON state to an OFF state, in response to a removal of a bias or signal applied on the nonpolar volatile two-terminal device. The nonpolar volatile two-terminal device is configured to automatically revert from an ON state to an OFF state, in response to a removal of a bias or signal applied on the nonpolar volatile two-terminal device.