BriefGPT.xyz
Mar, 2017
使用循环加权平均的序列数据机器学习
Machine Learning on Sequential Data Using a Recurrent Weighted Average
HTML
PDF
Jared Ostmeyer, Lindsay Cowell
TL;DR
该研究提出了一种新型的循环神经网络模型,即循环加权平均模型,它能够在处理符号时利用之前处理步骤的所有信息,表现强于标准LSTM模型。
Abstract
recurrent neural networks
(RNN) are a type of statistical model designed to handle
sequential data
. The model reads a sequence one symbol at a time. Each symbol is processed based on information collected from th
→