Deep Private-Feature Extraction
نویسندگان
چکیده
منابع مشابه
Deep Private-Feature Extraction
We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model which is trained and evaluated based on information theoretic constraints. Using the selective exchange of information between a user’s device and a service provider, DPFE enables the user to prevent certain sensitive information from being shared with a service provider, while allowing them to extract approved informat...
متن کاملUnsupervised Deep Autoencoders for Feature Extraction with Educational Data
The goal of this paper is to describe methods for automatically extracting features for student modeling from educational data, and students’ interaction-log data in particular, by training deep neural networks with unsupervised training. Several different types of autoencoder networks and structures are discussed, including deep neural networks, recurrent neural networks, variational autoencod...
متن کاملTraining Deep Neural Networks for Bottleneck Feature Extraction
In automatic speech recognition systems, preprocessing the audio signal to generate features is an important part of achieving a good recognition rate. Previous works have shown that artificial neural networks can be used to extract good, discriminative features that yield better recognition performance than manually engineered feature extraction algorithms. One possible approach for this is to...
متن کاملSupplement: Discrete Deep Feature Extraction: A Theory and New Architectures
For the handwritten digit classification experiment described in Section 6.1, Table 1 shows the classification error for Daubechies wavelets with 2 vanishing moments (DB2). Table 1. Classification errors in percent for handwritten digit classification using DB2 wavelet filters, different non-linearities, and different pooling operators For the feature importance experiment described in Section ...
متن کاملTopology Reduction in Deep Convolutional Feature Extraction Networks
Deep convolutional neural networks (CNNs) used in practice employ potentially hundreds of layers and 10,000s of nodes. Such network sizes entail significant computational complexity due to the large number of convolutions that need to be carried out; in addition, a large number of parameters needs to be learned and stored. Very deep and wide CNNs may therefore not be well suited to applications...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Knowledge and Data Engineering
سال: 2020
ISSN: 1041-4347,1558-2191,2326-3865
DOI: 10.1109/tkde.2018.2878698