Neuromorphic Synapse With Dual Memory For Plasticity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional computing architectures, such as the von Neumann architecture, are inefficient in terms of power consumption and space requirements compared to the human brain, prompting the need for neuromorphic systems that can efficiently emulate synaptic dynamics for effective neuromorphic networks.
Innovation Solution
A neuromorphic synapse apparatus comprising a synaptic device with a memory element and a control signal generator, where the memory element has both non-volatile and volatile characteristics to vary synaptic efficacy in response to programming and control signals, allowing for implementation of short-term and long-term synaptic plasticity rules.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If a non-volatile memory mechanism is used to store synaptic weight, then long-term weight updates are achieved, but the ability to implement short-term plasticity and dynamic synaptic behaviors is limited
Solution Approach 1:
The patent combines a non-volatile memory element (for long-term weight storage) with a volatile memory element (for short-term plasticity) into a single synaptic device. The non-volatile element maintains long-term synaptic weight updates while the volatile element dynamically adjusts conductance based on recent spike activity, enabling both LTP and STP effects simultaneously
Solution Approach 2:
The synaptic device is designed to perform multiple functions: storing long-term weight changes, implementing short-term plasticity, and enabling on-device tuning of synaptic dynamics. The dual-memory architecture allows the same device to exhibit both stable long-term memory and dynamic short-term adaptability
2Productivity
If conventional von Neumann architecture is used for computing, then processing demands can be met, but power consumption and space requirements increase significantly
Solution Approach 1:
The neuromorphic synapse performs computations locally at the synaptic weight storage location, eliminating the need to move data between separate memory and processing units. The synaptic device directly computes weighted sums by modulating conductance based on input spikes and current weight, achieving energy-efficient in-memory computing
3Productivity
If conventional von Neumann architecture is used for computing, then processing demands can be met, but space requirements increase significantly
Solution Approach 1:
The patent merges memory storage and processing functions into a single synaptic device. The non-volatile memory element stores synaptic weights while the volatile element and control circuitry perform computations, eliminating the need for separate memory modules and reducing overall system footprint
Data Source
AI summary
Neuromorphic synapse apparatus is provided comprising a synaptic device and a control signal generator. The synaptic device comprises a memory element, disposed between first and second terminals, for conducting a signal between those terminals with an efficacy which corresponds to a synaptic weight in a read mode of operation, and a third terminal operatively coupled to the memory element. The memory element has a non-volatile characteristic, which is programmable to vary the efficacy in response to programming signals applied via the first and second terminals in a write mode of operation, and a volatile characteristic which is controllable to vary the efficacy in response to control signals applied to the third terminal. The control signal generator is responsive to input signals and is adapted to apply control signals to the third terminal in the read and write modes, in dependence on the input signals, to implement predetermined synaptic dynamics.