Practical Implementation Report on Introducing Spec-Driven Development Using AI Agents in Software Development PBL
研究通过在软件开发项目课程中引入基于AI代理的规范驱动开发方法，解决了教育效果维持问题，采用定制化环境和四阶段工作流程，并强调教师定期验证代码理解的重要性。
0 citationsRead paper
Selected work
Representative Papers
Effects of Introducing Synaptic Scaling on Spiking Neural Network Learning
This work addresses the limited performance of spiking neural networks (SNNs) in unsupervised learning by integrating spike-timing-dependent plasticity (STDP) with L2-norm synaptic scaling within a winner-take-all (WTA) architecture. The study presents the first comprehensive evaluation of L2-norm synaptic scaling in SNN-based unsupervised learning, systematically investigating the effects of neuron count, STDP time constants, and synaptic weight normalization strategies. Experimental results demonstrate that the proposed approach significantly enhances classification accuracy under single-epoch training, achieving 88.84% on MNIST and 68.01% on Fashion-MNIST. These findings validate the efficacy and superiority of L2-norm synaptic scaling in improving unsupervised learning capabilities of SNNs.
0 citationsRead paper
Recent publications
Latest Papers
Practical Implementation Report on Introducing Spec-Driven Development Using AI Agents in Software Development PBL
研究通过在软件开发项目课程中引入基于AI代理的规范驱动开发方法，解决了教育效果维持问题，采用定制化环境和四阶段工作流程，并强调教师定期验证代码理解的重要性。
0 citationsRead paper
Effects of Introducing Synaptic Scaling on Spiking Neural Network Learning
This work addresses the limited performance of spiking neural networks (SNNs) in unsupervised learning by integrating spike-timing-dependent plasticity (STDP) with L2-norm synaptic scaling within a winner-take-all (WTA) architecture. The study presents the first comprehensive evaluation of L2-norm synaptic scaling in SNN-based unsupervised learning, systematically investigating the effects of neuron count, STDP time constants, and synaptic weight normalization strategies. Experimental results demonstrate that the proposed approach significantly enhances classification accuracy under single-epoch training, achieving 88.84% on MNIST and 68.01% on Fashion-MNIST. These findings validate the efficacy and superiority of L2-norm synaptic scaling in improving unsupervised learning capabilities of SNNs.
0 citationsRead paper