H2O学习笔记(五)——Deep Autoencoders
2016-10-26 16:02
1031 查看
先前的部分介绍了监督Deep Learning内容,Deep Learning 也可以用作非监督特征学习,尤其是在非线性降维方面。
Deep Autoencoders
Deep Autoencoders的原理可以看UFLDL的教程例子:Anomaly Detection
#Import ECG train and test data into the H2O cluster from h2o.estimators.deeplearning import H2OAutoEncoderEstimator import h2o h2o.init() train_ecg = h2o.import_file("http://h2o-public-test-data.s3.amazonaws.com/smalldata/anomaly/ecg_discord_train.csv") test_ecg = h2o.import_file("http://h2o-public-test-data.s3.amazonaws.com/smalldata/anomaly/ecg_discord_test.csv") train_ecg.describe() test_ecg.describe() #Train deep autoencoder learning model on "normal" # training data, y ignored anomaly_model = H2OAutoEncoderEstimator(activation="Tanh", hidden=[50,50,50], sparse=True, l1=1e-4, epochs=100) anomaly_model.train(x=train_ecg.names,training_frame=train_ecg) # Compute reconstruction error with the Anomaly # detection app (MSE between output and input layers) recon_error = anomaly_model.anomaly(test_ecg) print 'recon_error:',recon_error # Testing = Reconstructing the test dataset test_recon = anomaly_model.predict(test_ecg) print 'test_recon:',test_recon
相关文章推荐
- H2O的Deep Autoencoders
- Theano-Deep Learning Tutorials 笔记:Denoising Autoencoders (dA)
- DeepLearningToolBox学习——SAE(stacked auto encoders )
- Theano-Deep Learning Tutorials 笔记:Stacked Denoising Autoencoders (SdA)
- 深度学习笔记6:Learning color features with Sparse Autoencoders
- UFLDL学习笔记6(Linear Decoders with Autoencoders)
- [机器学习入门] 李弘毅机器学习笔记-17(Unsupervised Learning: Deep Auto-encoder;无监督学习:深度自动编码器)
- 论文笔记:Occlusion-free Face Alignment: Deep Regression Networks Coupled with De-corrupt Auto-Encoders
- Occlusion-free Face Alignment: Deep Regression Networks Coupled with De-corrupt AutoEncoders阅读笔记
- UFLDL 学习笔记——稀疏自动编码机(sparse autoencoder)
- [DeeplearningAI笔记]改善深层神经网络1.4_1.8深度学习实用层面_正则化Regularization与改善过拟合
- 深度学习代码注解(一)—— mnistdeepauto
- 菜鸡的学习笔记(一):DeepLab-ResNet Model代码中的相关知识点
- iOS学习笔记-错误-ARC forbids explicit message send of autorelease
- Neural Networks and Deep Learning 学习笔记(六)
- 深度学习 Deep Learning UFLDL 最新Tutorial 学习笔记 5:Softmax Regression
- Spring学习笔记(十):@Autowired和new的区别
- Fast.ai: Practical Deep Learning for coders 课程学习笔记:Part1 Lesson1 (Lesson0)
- .NET深入学习笔记(4):深拷贝与浅拷贝(Deep Copy and Shallow Copy)
- no auto summary的作用--学习笔记