提高液态机性能的输入模式探索
Exploration of Input Patterns for Enhancing the Performance of Liquid State Machines
摘要：
脉冲神经网络（SNN）以其低功耗的特点受到越来越多的关注。但是训练SNN是一个挑战。液态机（Liquid State Machine，LSM）作为储备池计算的一种主要类型，以其较低的训练成本得到了广泛的认可。探索LSM拓扑以提高性能通常需要超参数搜索，这既消耗资源又耗时。我们探讨的影响，输入规模减少LSM代替。研究LSM的投入减少主要有两个原因。一个是大图像的输入维度需要高效的处理。另一个是输入探索通常比架构搜索更经济。为了减轻LSM在有效处理巨大输入空间方面的困难，并发现输入减少是否可以提高LSM性能，我们探索了几种输入模式，即满量程，扫描线，棋盘和补丁。几个数据集已被用来评估所提出的输入模式的性能，包括两个空间图像数据集和一个时空图像数据库。实验结果表明，在棋盘模式下，减少输入使LSM的精度提高了5%，执行时间减少了50%，输入存储量减少了75%.
英文摘要：
Spiking Neural Networks (SNN) have gained increasing attention for its low power consumption. But training SNN is challenging. Liquid State Machine (LSM), as a major type of Reservoir computing, has been widely recognized for its low training cost among SNNs. The exploration of LSM topology for enhancing performance often requires hyper-parameter search, which is both resource-expensive and time-consuming. We explore the influence of input scale reduction on LSM instead. There are two main reasons for studying input reduction of LSM. One is that the input dimension of large images requires efficient processing. Another one is that input exploration is generally more economic than architecture search. To mitigate the difficulty in effectively dealing with huge input spaces of LSM, and to find that whether input reduction can enhance LSM performance, we explore several input patterns, namely fullscale, scanline, chessboard, and patch. Several datasets have been used to evaluate the performance of the proposed input patterns, including two spatio image datasets and one spatio-temporal image database. The experimental results show that the reduced input under chessboard pattern improves the accuracy by up to 5%, and reduces execution time by up to 50% with up to 75\% less input storage than the fullscale input pattern for LSM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
