Instead of introducing new learning algorithm for solving complex classification tasks, many research groups in machine learning have focused on creating a good feature representation. In addition, labeled data is oft...
详细信息
ISBN:
(纸本)9781467355797
Instead of introducing new learning algorithm for solving complex classification tasks, many research groups in machine learning have focused on creating a good feature representation. In addition, labeled data is often difficult and expensive to obtain sufficiently large amount of data. So, learning features from unlabeled data is proposed since unlabeled data is much easier to obtain than the labeled data. In this work, a highlevel feature representation is created by a sparse autoencoder with convolutional extraction. A sparse autoencoder is an unsupervised feedforward neural network that is trained to predict the input itself and has been widely used for learning good feature representation. A major advantage of this feature extraction approach not only provides good feature representation for higherlevel tasks but also can scale up to large images. However, there are several parameters that require careful selection to obtain high performance. The main objective in this work is to present a detailed analysis on the effect of receptive field resolution in handwritten classification based on MNIST database. In the experiment, the results show that receptive field resolution is one of the critical parameters to achieve state-of-the-art performance.
With the single-tube and double-tube fault of seven-level converter, this paper presents a new way to learn the faults feature based on the deep neural network of sparse autoencoder. sparse autoencoder is an unsupervi...
详细信息
With the single-tube and double-tube fault of seven-level converter, this paper presents a new way to learn the faults feature based on the deep neural network of sparse autoencoder. sparse autoencoder is an unsupervised learning method, it can learn the feature information of the fault data according to training. The feature information is used to train the softmax classifier by softmax regression to realize the aim of classification. Comparing with the traditional neural network of BP neural network, the experimental results show that the method to classify the fault of seven level converter based on deep neural network of sparse autoencoder can achieve higher accuracy.
暂无评论