Synaptic Resistors for Concurrent Signal Processing and Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current electronic devices cannot concurrently process signals and learn in parallel due to interference between voltage signals for processing and learning, requiring sequential modifications and external digital computing for accurate conductance modification, limiting their speed and energy efficiency.
Innovation Solution
The development of synaptic resistors (synstors) that integrate analog signal processing, learning, and memory functions in a single device, using a structure with input and output electrodes, a semiconducting channel, dielectric layer, charge storage material, and reference electrode, allowing for concurrent parallel signal processing and learning by applying specific voltage signals to modify conductance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If voltage signals are applied for learning to modify device conductance, then learning function is achieved, but signal processing is interrupted due to interference between learning and processing voltage signals
Solution Approach 1:
The device is segmented into distinct functional regions: a first region for signal processing and a second region for learning-induced conductance modification. By applying voltage signals to different regions simultaneously, the patent enables parallel execution of signal processing and learning operations without mutual interference, resolving the contradiction between learning adaptability and processing continuity.
Solution Approach 2:
The patent introduces a third electrode as an intermediary element that applies voltage signals to a specific region of the device. This intermediary electrode enables independent control of the learning region from the signal processing region, allowing simultaneous operation of both functions without direct interference between their voltage signals.
2Manufacturing precision
If sequential writing and reading processes are used to modify device conductance accurately, then manufacturing precision is improved, but speed and energy efficiency deteriorate
Solution Approach 1:
The patent employs periodic voltage signal application with specific timing characteristics to achieve accurate conductance modification. By using pulsed voltage signals with controlled duration and amplitude applied to specific regions, the device achieves precise learning-induced conductance changes without requiring iterative sequential processes, thereby improving both accuracy and speed.
Solution Approach 2:
The patent applies voltage signals with different characteristics to different regions of the device: signal processing voltages are applied to one region while learning voltages are applied to another region. This local differentiation allows each region to perform its specific function with optimized signal characteristics, achieving accurate conductance modification while maintaining high speed through parallel regional operations.
3Measurement precision
If external digital computing circuits are used to execute learning algorithms and obtain targeted conductances, then measurement precision is improved, but device complexity and energy consumption increase
Solution Approach 1:
The device performs learning-induced conductance modification autonomously through direct application of voltage signals to specific regions, without requiring external digital computing circuits to calculate target conductances. The device self-regulates its conductance changes based on the applied voltage signals, thereby reducing system complexity and energy consumption while maintaining learning functionality.
Solution Approach 2:
The patent merges the signal processing function and learning function into a single integrated device structure. By combining both functions in one device with spatially separated operational regions, the patent eliminates the need for separate external computing circuits, reducing overall system complexity while achieving accurate conductance modification through unified device operation.
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
Enables high-speed and energy-efficient concurrent parallel signal processing and learning, surpassing the limitations of existing devices by integrating signal processing and learning functions, achieving superior speed and power efficiency compared to computers and other electronic circuits.
Implementation Method 1
a dielectric layer disposed adjacent to the semiconducting channel, the dielectric layer disposed adjacent to the single side of the channel or the multiple sides of the channel; a reference electrode disposed adjacent to the dielectric layer; a charge storage material disposed within a portion of the dielectric layer
Implementation Method 2
a semiconducting channel connected between the input and output electrodes
Data Source
AI summary
Synaptic resistors (synstors), and their method of manufacture and integration into exemplary circuits are provided. Synstors are configured to emulate the analog signal processing, learning, and memory functions of synapses. Circuits incorporating synstors are capable of performing signal processing and learning concurrently in parallel analog mode with speed, energy efficiency, and functions superior to computers.