Muleta Kalkidan Deme, Kong Bai-Sun
IEEE Trans Biomed Circuits Syst. 2025 Apr;19(2):385-392. doi: 10.1109/TBCAS.2024.3446177. Epub 2025 Apr 2.
The spiking neural network (SNN) training with spike timing-dependent plasticity (STDP) for image classification usually requires a lot of neurons to extract representative features and(or) needs an external classifier. Conventional bio-inspired learning methods do not cover all possible learning opportunities, resulting in limited performance. We propose a new bio-plausible learning rule, target-modulated STDP (TSTDP), for higher learning efficiency and accuracy. We also propose an SNN architecture trainable with TSTDP using temporally encoded spikes to obtain higher accuracy and improved area efficiency without using an external classifier. Using the MNIST dataset, we have shown that the proposed design achieves an accuracy of 92%, which is up to 7% improvement compared to conventional networks of similar sizes. For providing similar accuracy, up to 75% smaller network size has been shown on top of demonstrating stronger resilience to process variations. Benchmarking on the CIFAR-10 and neuromorphic DVS gesture datasets show an accuracy improvement of up to 12.4% and 3.6%, respectively.
用于图像分类的基于脉冲时间依赖可塑性（STDP）的脉冲神经网络（SNN）训练通常需要大量神经元来提取代表性特征，并且（或者）需要外部分类器。传统的受生物启发的学习方法没有涵盖所有可能的学习机会，导致性能有限。我们提出了一种新的具有生物合理性的学习规则——目标调制STDP（TSTDP），以提高学习效率和准确性。我们还提出了一种可使用TSTDP进行训练的SNN架构，该架构使用时间编码脉冲，无需外部分类器即可获得更高的准确性和更高的面积效率。使用MNIST数据集，我们已经表明，所提出的设计实现了92%的准确率，与类似规模的传统网络相比提高了7%。在提供相似准确率的情况下，所展示的网络规模比传统网络小75%，同时还表现出对工艺变化更强的鲁棒性。在CIFAR-10和神经形态DVS手势数据集上的基准测试表明，准确率分别提高了12.4%和3.6%。
