论文标题
与尖峰神经网络的类比和关系推理
Analogical and Relational Reasoning with Spiking Neural Networks
论文作者
论文摘要
Raven的进步矩阵已被广泛用于测量人类的抽象推理和智力。但是，对于人工学习系统，抽象推理仍然是一个具有挑战性的问题。在本文中，我们研究了如何通过生物学启发的尖峰模块增强神经网络在解决此问题方面具有重要优势。为了说明这一点，我们首先通过有监督的学习来研究网络的性能，然后通过无监督的学习进行研究。 Raven数据集的实验表明，我们监督网络的总体准确性超过了人类水平的性能，而我们的无监督网络的表现显着胜过现有的无监督方法。最后，我们来自受监督和无监督的学习的结果表明，与他们的非官能相关组件不同，带有尖峰模块的网络能够在没有任何明确指令的情况下提取和编码时间功能，并且不会严重依靠培训数据，并且更容易将其推广到新问题。总而言之，此处报告的结果表明，具有峰值模块的人工神经网络非常适合解决抽象的推理。
Raven's Progressive Matrices have been widely used for measuring abstract reasoning and intelligence in humans. However for artificial learning systems, abstract reasoning remains a challenging problem. In this paper we investigate how neural networks augmented with biologically inspired spiking modules gain a significant advantage in solving this problem. To illustrate this, we first investigate the performance of our networks with supervised learning, then with unsupervised learning. Experiments on the RAVEN dataset show that the overall accuracy of our supervised networks surpass human-level performance, while our unsupervised networks significantly outperform existing unsupervised methods. Finally, our results from both supervised and unsupervised learning illustrate that, unlike their non-augmented counterparts, networks with spiking modules are able to extract and encode temporal features without any explicit instruction, do not heavily rely on training data, and generalise more readily to new problems. In summary, the results reported here indicate that artificial neural networks with spiking modules are well suited to solving abstract reasoning.
