Multilayer perceptron architectures for data compression tasks
نویسنده
چکیده
Different kinds of Multilayer Perceptrons, using a back-propagation learning algonthm, have been used to perform data compression tasks. Depending upon the architecture and the type of problern learned to solve ( classification or auto-association), the networks provide different kinds of dimensionality reduction preserving different properties of the data space. Some experiments show that usmg the non-linearities of the MLP units may improve performances of classical linear dimensionality reduction. All the experiments reported here have been carried out on speech data.
منابع مشابه
Classification of Storm Events Using a Fuzzy Encoded Multilayer Perceptron
Volumetric radar data are used to detect severe summer storm events but discriminating between storm event types is a challenge due to the high dimensionality and amorphous nature of the data, the paucity of data labeled through an external independent reference test, and the imprecision of the class labels. Two multilayer perceptron architectures are used to discriminate between two types of s...
متن کاملAn emphasized target smoothing procedure to improve MLP classifiers performance
Standard learning procedures are better fitted to estimation than to classification problems, and focusing the training on appropriate samples provides performance advantages in classification tasks. In this paper, we combine these ideas creating smooth targets for classification by means of a convex combination of the original target and the output of an auxiliary classifier, the combination p...
متن کاملSupervised SOM Based Architecture versus Multilayer Perceptron and RBF Networks
We address a contrastive study between the well known Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) neural networks and a SOM based supervised architecture in a number of data classification tasks. Well known databases like Breast Cancer, Parkinson and Iris were used to evaluate the three architectures by constructing confusion matrices. The results are encouraging and indicate t...
متن کاملSingle channel source separation with general stochastic networks
Single channel source separation (SCSS) is ill-posed and thus challenging. In this paper, we apply general stochastic networks (GSNs) – a deep neural network architecture – to SCSS. We extend GSNs to be capable of predicting a time-frequency representation, i.e. softmask by introducing a hybrid generative-discriminative training objective to the network. We evaluate GSNs on data of the 2nd CHiM...
متن کاملBelief Propagation for Error Correting Codes and Lossy Compression Using Multilayer Perceptrons
The belief propagation (BP) based algorithm is investigated as a potential decoder for both of error correcting codes and lossy compression, which are based on non-monotonic tree-like multilayer perceptron encoders. We discuss that whether the BP can give practical algorithms or not in these schemes. The BP implementations in those kind of fully connected networks unfortunately shows strong lim...
متن کامل