In this paper, we present our recent progress on multi-layer perceptron (MLP) based data-driven feature extraction using improved MLP structures. Four-layer MLPs are used in this study. Different signal processing methods are applied before the input layer of the MLP. We show that the first hidden layer of a four-layer MLP is able to detect some basic patterns from the time-frequency plane. KLT...

In this contribution, human face as biometric [1] is considered. Original method of feature extraction from image data is introduced using MLP (multilayer perceptron) and PCA (principal component analysis). This method is used in human face recognition system and results are compared to face recognition system using PCA directly, to a system with direct classification of input images by MLP and...

Gaussian Mixture Model (GMM) and Multi Layer Perceptron (MLP) based acoustic models are compared on a French large vocabulary continuous speech recognition (LVCSR) task. In addition to optimizing the output layer size of the MLP, the effect of the deep neural network structure is also investigated. Moreover, using different linear transformations (time derivatives, LDA, CMLLR) on conventional M...

Monotremes (platypus and echidna) are the descendants of the oldest ancestor of all extant mammals distinguished from other mammals by mode of reproduction. Monotremes lay eggs following a short gestation period and after an even briefer incubation period, altricial hatchlings are nourished over a long lactation period with milk secreted by nipple-less mammary patches located on the female's ab...

PICOT (protein kinase C-interacting cousin of thioredoxin) was previously shown to inhibit pressure overload-induced cardiac hypertrophy, concomitant with an increase in ventricular function and cardiomyocyte contractility. The combined analyses of glutathione S-transferase pull-down experiments and mass spectrometry enabled us to determine that PICOT directly interacts with muscle LIM protein ...

In this contribution we present results of using possibly inaccurate knowledge of model derivatives as part of the training data for a multilayer perceptron network (MLP). Even simple constraints ooer signiicant improvements and the resulting models give better prediction performance than traditional data driven MLP models.

Speaker independent vowel recognition is a di cult pattern recognition problem. Recently therehas been much research using Multi-Layer Perceptrons (MLP) and Decision Trees for this task. Thispaper presents a new approach to this problem. A new neural architecture and learning algorithmcalled Neural Tree Networks (NTN) are developed. This network uses a tree structure with a neural<l...

In 2000, Balamurali and Govindaraju presented the modified tightened two-level continuous sampling plan (modified MLP-T-2 plan). This paper explores the problem of minimizing the average fraction inspected (AFI) for a modified MLP-T-2 plan. The solution procedure is developed to find the optimal parameters that will meet the average outgoing quality limit (AOQL) requirement, while also minimizi...

We propose an active learning method with hidden-unit reduction, which is devised specially for multilayer perceptrons (MLP). First, we review our active learning method, and point out that many Fisher-information-based methods applied to MLP have a critical problem: the information matrix may be singular. To solve this problem, we derive the singularity condition of an information matrix, and ...