搜索资源列表
insuranceQA-cnn-lstm-master
- 这是一个保险语料的一个简单的问答系统，采用cnn和lstm分别进行试验，分别验证效果的改变，文件包括两个版本，tensorflow和theano。(This is a simple question answering system for insurance corpus, which is tested by CNN and LSTM respectively, and the results are verified separately. The document consists of
LSTM-MATLAB-master
- code Matlab LSTM by mounira
RNN_LSTM-master
- descr iption de code RNN LSTM
LSTM
- 用于运行LSTM的预测代码，例子是国际航班客流量。使用语言为python.(The forecast code used to run LSTM is an example of international flight traffic. The language used is python.)
zh_lstm
- lstm做情感分类,中文，用到豆瓣影评，结巴分词，lstm模型，环境python3做编码处理。(lstm for sentiment analyse)
lstm_multi_gpu
- lstm 实现情感分析的多GPU版本，用于处理的语料数据很大的时候，加速训练过程。(lstm multi gpu for sentiment analysis)
lstm
- lstm 单gpu版本; lstm 做sentiment analysis的0版本实现; 简单的入门实现;(lstm for single-gpu ; tuturial)
seq-lstm
- 用pytorch实现基于lstm长短时网络的词性判断程序(Using pytorch to implement a speech judgment program based on LSTM length and short time network)
LSTM
- python实现的LSTM, 可以放心学习，有兴趣研究LSTM编码的同学，可收藏(Python implementation of the LSTM, can rest assured of learning, interested in the study of LSTM code of the students, can be collected)
MyPro
- LSTM RNN python machine learning
lstm
- 机器学习中的lstm，希望对大家有用，谢谢啦(Lstm in machine learning, hope to be useful to everyone, thank you)
lstm
- 使用lstm神经网络预测时间序列，同时对参数选择进行优化(Time series prediction using LSTM neural network, the selection of the parameters are optimized)
lstm
- 循环神经网络LSTM可以预测时间序列数据，根据历史时刻的信息预测未来时刻的信息(the recurrent neural network is very useful to predict data in the future)
LSTM-单变量多步
- 用jupyter notebook 实现深度学习LSTM单变量多步的时间序列预测(Using jupyter notebook to realize multi-step time series prediction of deep learning LSTM)
LSTM预测
- 可以用于LSTM预测，数据，和权重更新程序已上传(Can be used for LSTM prediction)
LSTM
- lstm时间预测matlab代码。程序说明：DATA.mat 是一行时序值， numdely 是用前numdely个点预测当前点，cell_num是隐含层的数目，cost_gate 是误差的阈值。直接在命令行输入RunLstm(numdely,cell_num,cost_gate)即可(This is the matlab code of LSTM time prediction. Program descr iption: data.mat is a row of sequential va
LSTM-Human-Activity-Recognition-master
- 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
emd-lstm
- 基于经验模态分解成多个模态和一个残余量，再利用长短神经网络预测分别训练每一个模态和残余量，最后重构结果，得到预测结果(Prediction based on empirical mode decomposition and long short neural network)
stock_predict_with_LSTM-master
- 基于python的LSTM做股票预测源代码(Based on Python LSTM stock forecast source code)
LSTM
- 属于lstm的matlab给出的示例，使用代码进行自我学习非常好用(Belongs to the LSTM matlab example, using code for self-learning is very easy to use)