首页> 外文会议>International work-conference on artificial and natural neural networks >Digital Connectionist Hardware: Current Problems and Future Challenges
【24h】

Digital Connectionist Hardware: Current Problems and Future Challenges

机译:数字连接员硬件:当前问题和未来的挑战

获取原文

摘要

this paper reviews some representative digital systems for neural computation which have been described in the scientific literature and, in some cases, marketed. The descriptions of these systems are arranged somehow chronologically to show the basic trends of hardware for artificial neural networks. With the help of these examples, some parameters for a taxonomy are outlined and used to contrast the diverse features of the described systems. Comparisons also require the evaluation of performances, and some problems typical of this task are discussed. A concluding section attempts a synthesis of the problems so far encountered by digital connectionist hardware in becoming practical and attractive. The future challenges of the domain are tentatively identified.
机译:本文介绍了一些用于科学文学中的神经计算的代表性数字系统,并在某些情况下销售。按时间顺序排列这些系统的描述以显示人工神经网络的硬件的基本趋势。在这些示例的帮助下,概述了分类法的一些参数,并用于对比所描述的系统的不同特征对比。比较还需要对性能的评估,并讨论了这项任务的典型问题。结论部分试图综合数字连接主人硬件遇到的问题,以实际和吸引力。暂定识别域的未来挑战。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号