A Comparison of Neuromorphic Classification Tasks
A Comparison of Neuromorphic Classification Tasks
复制标题
神经形态分类任务的比较
DOI：
10.1145/3229884.3229896
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
G. Rose
中科院分区：
文献类型：
--
作者：
John J. M. Reynolds;J. Plank;Catherine D. Schuman;Grant Bruer;A. Disney;Mark E. Dean;G. Rose
在过去的十年中，出现了各种神经网络模型和机器学习技术，它们在图像分类方面的成功令人惊叹。对于其他分类任务，选择和配置神经网络解决方案并不简单。在本文中，我们评估和比较了各种神经网络模型，通过各种机器学习技术进行训练，用于各种分类任务。虽然深度学习通常表现出最好的分类准确性，但我们注意到水库计算的前景，以及对尖峰神经网络的进化优化。在许多情况下，这些技术的性能与深度学习一样好，甚至更好，并且由此产生的网络比深度学习的网络要小得多。
A variety of neural network models and machine learning techniques have arisen over the past decade, and their successes with image classification have been stunning. With other classification tasks, selecting and configuring a neural network solution is not straightforward. In this paper, we evaluate and compare a variety of neural network models, trained by a variety of machine learning techniques, on a variety of classification tasks. While Deep Learning typically exhibits the best classification accuracy, we note the promise of Reservoir Computing, and evolutionary optimization on spiking neural networks. In many cases, these technologies perform as well as, or better than Deep Learning, and the resulting networks are much smaller than their Deep Learning counterparts.