多级输入的神经网络容量
Neural Network Capacity for Multilevel Inputs
摘要:
本文研究了广义神经网络的记忆能力。Hopfield网络训练与各种学习技术的研究,他们的能力都为二进制和非二进制字母。结果表明,当使用多电平输入时,容量可以大大增加。提出了新的学习策略,以增加Hopfield网络的容量,这些方法的可扩展性也检查在网络的大小。对于容量增加的网络,检查了从单个神经元的刺激中回忆整个模式的能力。
英文摘要:
This paper examines the memory capacity of generalized neural networks. Hopfield networks trained with a variety of learning techniques are investigated for their capacity both for binary and non-binary alphabets. It is shown that the capacity can be much increased when multilevel inputs are used. New learning strategies are proposed to increase Hopfield network capacity, and the scalability of these methods is also examined in respect to size of the network. The ability to recall entire patterns from stimulation of a single neuron is examined for the increased capacity networks.
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。