A general problem in model selection is to obtain the right parameters that make a model t observed data. If the model selected is a Multilayer Perceptron (MLP) trained with Backpropagation (BP), it is necessary to nd appropriate initial weights and learning parameters. This paper proposes a method that combines Simulated Annealing (SimAnn) and BP to train MLPs with a single hidden layer, terme...

This paper describes a pattern recognition algorithm for the location of the points of vocal fold closure in a noisy speech signal. The algorithm uses a multi-layer perceptron (MU) classifier with inputs from a window on the speech signal, and an output signifying the presence of a vocal fold closure at the centre of the window. The location of the vocal fold closures, or the fundamental period...

In the area of information processing one fundamental issue is how to measure the statistical relationship between two variables based only on their samples. In a previous paper, the idea of Information Potential which was formulated from the so called Quadratic Mutual Information was introduced, and successfully applied to problems such as Blind Source Separation and Pose Estimation of SAR (Sy...

An autoadaptive neuro-fuzzy segmentation and edge detection architecture is presented. The system consists of a multilayer perceptron (MLP)-like network that performs image segmentation by adaptive thresholding of the input image using labels automatically pre-selected by a fuzzy clustering technique. The proposed architecture is feedforward, but unlike the conventional MLP the learning is unsu...

Dr. David Shahian Lahey Clinic Burlington, MA 01805 Experiments demonstrated that sigmoid multilayer perceptron (MLP) networks provide slightly better risk prediction than conventional logistic regression when used to predict the risk of death, stroke, and renal failure on 1257 patients who underwent coronary artery bypass operations at the Lahey Clinic. MLP networks with no hidden layer and ne...

Consider a multilayer perceptron (MLP) with d inputs, a single hidden sigmoidal layer and a linear output. By adding an additional d inputs to the network with values set to the square of the rst d inputs, properties reminiscent of higher-order neural networks and radial basis function networks (RBFN) are added to the architecture with little added expense in terms of weight requirements. Of pa...

This paper presents an adaptation of the Multi-Layer Perceptron (MLP) algorithm for use in predicting diabetes risk. The aim is to enhance accuracy and generalizability model by incorporating preprocessing techniques, dimensionality reduction using Principal Component Analysis (PCA), improvements optimization regularization. Several factors, including glucose level, pregnancy, blood pressure, b...

Mapping brain activity patterns in external actions has been studied in recent decades and is the base of a brain-computer interface. This type of interface is extremely useful for people with disabilities, where one can control robotic systems that assist, or even replace, non functional body members. Part of the studies in this area focuses on noninvasive interfaces, in order to broaden the i...

This paper proposes an utterance veri cation system for hidden Markov model (HMM) based automatic speech recognition systems. A veri cation objective function, based on a multi-layer-perceptron (MLP), is adopted which combines con dence measures from both the recognition and veri cation models. Discriminative minimum veri cation error training is applied for optimizing the parameters of the MLP...

The two processing paradigms of Genetic Algorithms (GAs) and Neural Networks (NNs) are combined to form a hybrid system to act as an adaptive pattern evolution device; this system is subsequently applied to a musical composition task. GAs are well suited to algorithmic musical composition, due to the complex nature of the search space of this task. Previous applications of GAs to musical compos...