Novel pulse neural network synaptic weight adjustment method
By introducing Leaky Integrate and Fired algorithm and Q learning mechanism into pulsed neural networks, combined with Gaussian pulse timing dependence plasticity rules, the shortcomings of traditional rules in weight adjustment are solved, and more efficient pulsed neural network weight adjustment and classification task accuracy are achieved.
CN119647531AActive Publication Date: 2025-03-18KUNMING UNIV OF SCI & TECH
3 Cites 3 Cited by
Patent Information
- Application Number
- CN202411458895.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-18
- Publication Date
- 2025-03-18
- Estimated Expiration
- 2044-10-18
AI Technical Summary
Technical Problem
The weight adjustment results of traditional pulse timing-dependent plasticity rules in pulse neural networks are not ideal, and the global adjustment of neuronal weights cannot be achieved.
Method used
By introducing the Leaky Integrate and Fired algorithm, the pulse neural network model is built, and the time interval between neurons before and after synapses is tracked, local weight adjustment is performed in combination with Gaussian pulse timing dependence rules, and global weight adjustment is achieved through the Q-learning mechanism.
Benefits of technology
The accuracy of pulsed neural networks in classification tasks is improved, effective local and global regulation of synaptic weights is achieved, and effective connections between neurons are enhanced.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention relates to a novel pulse neural network synaptic weight adjustment method, and belongs to the field of artificial intelligence. Firstly, a traditional pulse time sequence dependence plasticity rule is improved based on the distribution trend of a Gaussian function, so that the weight change corresponding to the optimized synaptic plasticity rule when the time interval tends to 0 is larger, and when the time interval is gradually increased, the weight change is in an accelerated descending trend; the method comprises the following steps: firstly, performing synaptic weight local regulation on a neuron model to improve the local regulation capability of the synaptic plasticity of the neuron, then introducing reinforcement learning, associating Q learning with the synaptic plasticity in the neuron model, and realizing the global regulation and control of the plasticity on the basis of the synaptic weight local regulation. According to the above synaptic plasticity rule, the spiking neural network constructed based on Leaky Integrating and Fire is subjected to weight adjustment, so that the spiking neural network has better performance.
Need to check novelty before this filing date? Find Prior Art