arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1604.05897cs.ETcs.ARcs.DC
收藏

CLAASIC:一种受皮层启发的硬件加速器

CLAASIC: a Cortex-Inspired Hardware Accelerator

Valentin Puente, José Ángel Gregorio

AI总结:

本文提出受皮层学习算法启发的硬件加速器CLAASIC,通过分组交换网络实现可扩展架构,相比软件实现性能提升4个数量级、能效提升8个数量级,并节省90%通信成本。

摘要:

本研究探索了专用硬件实现皮层学习算法(Cortical Learning Algorithm,CLA)的可行性,以充分发挥其固有优势。该算法受当前对哺乳动物新皮层的理解启发,是分层时序记忆(Hierarchical Temporal Memory,HTM)的基础。与其他机器学习(ML)方法相比,其结构不依赖于具体应用,并依赖完全无监督的持续学习。我们假设硬件实现不仅能够将这些思想已有的实际用途扩展到更广泛的场景,而且能够利用CLA对硬件友好的特性。所提出的架构将使软件方案无法实现的扩展性成为可能,并充分利用CLA众多优势之一:低计算需求和低存储占用。与最先进的CLA软件实现相比,性能有望提升4个数量级,能效提升最高可达8个数量级。我们建议采用分组交换网络来解决这一问题。本文讨论了该方法的基本问题,并提出了实现可扩展方案的解决思路。我们将使用成熟的架构技术和工具分析成本和性能。所得结果表明,即使在CMOS技术下,在受限成本条件下,也有可能实现大规模系统。我们发现,所提出的解决方案在运行合成负载或真实负载时,能够节省90%的原始通信成本。

英文摘要:

This work explores the feasibility of specialized hardware implementing the Cortical Learning Algorithm (CLA) in order to fully exploit its inherent advantages. This algorithm, which is inspired in the current understanding of the mammalian neo-cortex, is the basis of the Hierarchical Temporal Memory (HTM). In contrast to other machine learning (ML) approaches, the structure is not application dependent and relies on fully unsupervised continuous learning. We hypothesize that a hardware implementation will be able not only to extend the already practical uses of these ideas to broader scenarios but also to exploit the hardware-friendly CLA characteristics. The architecture proposed will enable an unfeasible scalability for software solutions and will fully capitalize on one of the many CLA advantages: low computational requirements and reduced storage utilization. Compared to a state-of-the-art CLA software implementation it could be possible to improve by 4 orders of magnitude in performance and up to 8 orders of magnitude in energy efficiency. We propose to use a packet-switched network to tackle this. The paper addresses the fundamental issues of such an approach, proposing solutions to achieve scalable solutions. We will analyze cost and performance when using well-known architecture techniques and tools. The results obtained suggest that even with CMOS technology, under constrained cost, it might be possible to implement a large-scale system. We found that the proposed solutions enable a saving of 90% of the original communication costs running either synthetic or realistic workloads.

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。

↑