Acoustic feature development during unsupervised learning by a neural net
نویسندگان
چکیده
منابع مشابه
Unsupervised feature learning by augmenting single images
When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm. In this paper we investigate if it is possible to use data augmentation as the main component of an unsupervised feature learning architecture. To that end we sa...
متن کاملUnsupervised Feature Learning by Deep Sparse Coding
In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks. The main innovation of the framework is that it connects the sparse-encoders from different layers by a sparse-to-dense module. The sparse-to-dense module is a composition of a local spatial poo...
متن کاملDiscriminative Unsupervised Feature Learning with Convolutional Neural Networks
Current methods for training convolutional neural networks depend on large amounts of labeled samples for supervised training. In this paper we present an approach for training a convolutional neural network using only unlabeled data. We train the network to discriminate between a set of surrogate classes. Each surrogate class is formed by applying a variety of transformations to a randomly sam...
متن کاملComparison of Bayesian and Neural Net Unsupervised
Unsupervised classiication is the classiication of data into a number of classes in such a way that data in each class are all similar to each other. In the past there have been few if any studies done to compare the performance of diierent unsupervised classiication techniques. In this paper we review Bayesian and neural net approaches to unsupervised classiication and present results of exper...
متن کاملFeature Selection for Unsupervised Learning
In this paper, we identify two issues involved in developing an automated feature subset selection algorithm for unlabeled data: the need for finding the number of clusters in conjunction with feature selection, and the need for normalizing the bias of feature selection criteria with respect to dimension. We explore the feature selection problem and these issues through FSSEM (Feature Subset Se...
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: The Journal of the Acoustical Society of America
سال: 1989
ISSN: 0001-4966
DOI: 10.1121/1.2027604