文件名称:LSTM-Human-Activity-Recognition-master
介绍说明--下载内容来自于网络,使用问题请自行百度
与经典的方法相比,使用具有长时间记忆细胞的递归神经网络(RNN)不需要或几乎不需要特征工程。数据可以直接输入到神经网络中,神经网络就像一个黑匣子,可以正确地对问题进行建模。其他研究在活动识别数据集上可以使用大量的特征工程,这是一种与经典数据科学技术相结合的信号处理方法。这里的方法在数据预处理的数量方面非常简单(Compared with the classical methods, the recursive neural network (RNN) with long-term memory cells does not need or almost need feature engineering. Data can be directly input into the neural network, which acts as a black box and can correctly model the problem. Other research can use a lot of Feature Engineering on activity recognition data sets, which is a signal processing method combined with classical data science and technology. The method here is very simple in terms of the number of data preprocessing)
(系统自动生成,下载前可以参看下载内容)
下载文件列表
文件名 | 大小 | 更新时间 |
---|---|---|
LSTM-Human-Activity-Recognition-master | 0 | 2019-04-16 |
LSTM-Human-Activity-Recognition-master\.gitignore | 24 | 2019-04-16 |
LSTM-Human-Activity-Recognition-master\LICENSE | 1086 | 2019-04-16 |
LSTM-Human-Activity-Recognition-master\LSTM.ipynb | 213291 | 2019-04-16 |
LSTM-Human-Activity-Recognition-master\LSTM_files | 0 | 2019-04-16 |
LSTM-Human-Activity-Recognition-master\LSTM_files\LSTM_16_0.png | 77480 | 2019-04-16 |
LSTM-Human-Activity-Recognition-master\LSTM_files\LSTM_18_1.png | 43286 | 2019-04-16 |
LSTM-Human-Activity-Recognition-master\README.md | 30154 | 2019-04-16 |
LSTM-Human-Activity-Recognition-master\data | 0 | 2019-04-16 |
LSTM-Human-Activity-Recognition-master\data\.gitignore | 33 | 2019-04-16 |
LSTM-Human-Activity-Recognition-master\data\download_dataset.py | 914 | 2019-04-16 |
LSTM-Human-Activity-Recognition-master\data\source.txt | 2068 | 2019-04-16 |
本网站为编程资源及源代码搜集、介绍的搜索网站,版权归原作者所有! 粤ICP备11031372号
1999-2046 搜珍网 All Rights Reserved.