Ferroelectric Transistor Synapse for Multi-State Neuromorphic Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current neuromorphic devices lack the ability to achieve multiple resistance state levels, limiting their capacity to learn and process various data patterns effectively.
Innovation Solution
A synapse system incorporating a ferroelectric transistor and a resistive element connected in series, with a selecting controller and lines, allows for multiple resistance state levels by adjusting the polarization voltage of the ferroelectric transistor, enabling the synapse to have multiple synaptic levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If a conventional synaptic system is used, then the device structure is simple, but the number of resistance state levels is limited
Solution Approach 1:
The patent applies parameter changes by utilizing the ferroelectric transistor's gate voltage parameter to control the resistive element's resistance state. By varying the gate voltage applied to the ferroelectric transistor, the synapse can achieve multiple resistance state levels (at least three distinct levels), transforming a single-state resistive element into a multi-state synaptic weight element through electrical parameter modulation.
2Adaptability or versatility
If multiple resistance state levels are achieved, then the learning capability is improved, but the power consumption increases
Solution Approach 1:
The ferroelectric transistor provides self-service functionality through its non-volatile memory characteristic. The ferroelectric material in the gate retains polarization states without requiring continuous power supply, allowing the synapse to maintain multiple resistance states passively. This eliminates the need for constant refresh operations that would consume power, enabling the system to achieve enhanced learning capability with reduced power consumption compared to volatile memory-based approaches.
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 configuration enhances the neuromorphic device's ability to process data patterns by allowing multiple synaptic levels, improving learning capabilities and reducing power consumption through controlled transistor current adjustments.
Implementation Method 1
a synapse system of a neuromorphic device including a ferroelectric transistor
Data Source
AI summary
A synapse system of a neuromorphic device may include a pre-synaptic neuron; a pre-synaptic line extending from the pre-synaptic neuron in a first direction; a post-synaptic neuron; a post-synaptic line extending from the post-synaptic line in a second direction; a selecting controller; a selecting line extending from the selecting controller in a third direction; and a synapse electrically connected with the pre-synaptic line, the post-synaptic line, and the selecting line.