首页> 外文OA文献 >Deep counter networks for asynchronous event-based processing
【2h】

Deep counter networks for asynchronous event-based processing

机译:深度计数器网络,用于基于事件的异步处理

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

Despite their advantages in terms of computational resources, latency, and power consumption, event-based implementations of neural networks have not been able to achieve the same performance figures as their equivalent state-of-the-art deep network models. We propose counter neurons as minimal spiking neuron models which only require addition and comparison operations, thus avoiding costly multiplications. We show how inference carried out in deep counter networks converges to the same accuracy levels as are achieved with state-of-the-art conventional networks. As their event-based style of computation leads to reduced latency and sparse updates, counter networks are ideally suited for efficient compact and low-power hardware implementation. We present theory and training methods for counter networks, and demonstrate on the MNIST benchmark that counter networks converge quickly, both in terms of time and number of operations required, to state-of-the-art classification accuracy.
机译:尽管它们在计算资源,延迟和功耗方面具有优势,但基于事件的神经网络实现仍无法获得与其等效的最新深层网络模型相同的性能指标。我们提出将反神经元作为最小加标神经元模型,该模型仅需要加法和比较操作,从而避免了昂贵的乘法。我们将展示在深度计数器网络中进行的推理如何收敛到与最先进的常规网络相同的精度水平。由于其基于事件的计算方式可减少延迟和稀疏更新,因此计数器网络非常适合高效紧凑和低功耗的硬件实现。我们提供了计数器网络的理论和训练方法,并在MNIST基准上证明了计数器网络在时间和所需操作数方面都可以迅速收敛,从而达到最新的分类精度。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利

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