The 2011 International Joint Conference on Neural Networks

The Levenberg-Marquardt algorithm is one of the most common choices for training medium-size artificial neural networks. Since it was designed to solve nonlinear least-squares problems, its applications to the training of neural networks have so far typically amounted to using simple regression even for classification tasks. However, in this case the cross-entropy function, which corresponds to th... View full abstract»

Probabilistic record linkage has been used for many years in a variety of industries, including medical, government, private sector and research groups. The formulas used for probabilistic record linkage have been recognized by some as being equivalent to the naïve Bayes classifier. While this method can produce useful results, it is not difficult to improve accuracy by using one of a host of othe... View full abstract»

Conventional techniques are often unable to achieve the Fetal Electrocardiogram FECG extraction and R-peak detection in FECG from the abdominal ECG (AECG) in satisfactorily level for Fetal Heart Rate (FHR) monitoring. A new methodology by combining the Artificial Neural Network (ANN) and Correlation approach has been proposed in this paper. Artificial Neural Network is chosen primarily since it is... View full abstract»

This paper attempts to formulate the behavioral pattern of smart homes user activities. Smart homes depend on effective representation of residents' activities into ubiquitous computing elements. User activities inside a home follow specific temporal patterns, which are predictable utilizing statistical analysis. This paper intended to develop a temporal learning algorithm to find out the time dif... View full abstract»

A robust model predictive control (MPC) method is proposed for nonlinear affine systems with bounded disturbances. The robust MPC technique requires on-line solution of a minimax optimal control problem. The minimax strategy means that worst-case performance with respect to uncertainties is optimized. The minimax optimization problem involved in robust MPC is reformulated to a minimization problem... View full abstract»

In this paper a new nonlinear digital baseband predistorter design is introduced based on direct learning, together with a new Wiener system modeling approach for the high power amplifiers (HPA) based on the B-spline neural network. The contribution is twofold. Firstly, by assuming that the nonlinearity in the HPA is mainly dependent on the input signal amplitude the complex valued nonlinear stati... View full abstract»

A low-order model (LOM) of biological neural networks, which is biologically plausible, is herein reported. LOM is a recurrent hierarchical network composed of novel models of dendritic trees for encoding information, spiking neurons for computing subjective probability distributions and generating spikes, nonspiking neurons for transmitting inhibitory graded signals to modulate their neighboring ... View full abstract»

Complex network provides a general scheme for machine learning. In this paper, we propose a competitive learning mechanism realized on large scale networks, where several particles walk in the network and compete with each other to occupy as many nodes as possible. Each particle can perform a random walk by choosing any neighbor to visit, a deterministic walk by choosing to visit the node with the... View full abstract»

In this paper, a neural-network-based optimal control scheme for a class of nonlinear discrete-time systems with control constraints is proposed. The iterative adaptive dynamic programming (ADP) algorithm via globalized dual heuristic programming (GDHP) technique is developed to design the optimal controller with convergence proof. Three neural networks are used to facilitate the implementation of... View full abstract»

A new ε-optimal control algorithm based on the adaptive dynamic programming (ADP) is proposed to solve the finite horizon optimal control problem for a class of discrete-time nonlinear systems with unfixed initial state. The proposed algorithm makes the performance index function converges iteratively to the greatest lower bound of all performance indices within an error bound according to ε with ... View full abstract»

Word burstiness phenomenon, which means that if a word occurs once in a document it is likely to occur repeatedly, has interested the text analysis field recently. Dirichlet Compound Multinomial Latent Dirichlet Allocation (DCMLDA) introduces this word burstiness mechanism into Latent Dirichlet Allocation (LDA). However, in DCMLDA, there is no restriction on the word burstiness intensity of each t... View full abstract»

Extreme energy ratio (EER) is a recently proposed feature extractor to learn spatial filters for electroencephalogram (EEG) signal classification. It is theoretically equivalent and computationally superior to the common spatial patterns (CSP) method which is a widely used technique in brain-computer interfaces (BCIs). However, EER may seriously overfit on small training sets due to the presence o... View full abstract»

How could synapse number and position on a dendrite affect neuronal behavior with respect to the decoding of firing rate and temporal pattern? We developed a model of a neuron with a passive dendrite and found that dendritic length and the particular synapse positions directly determine the behavior of the neuron in response to patterns of received inputs. We revealed two distinct types of behavio... View full abstract»

The paper shows rigorously how to build a KWTA selector from a classical neural Hopfield network in continuous time. The analytical relations between parameters result in a step-by-step accurate and flexible procedure to calculate the amplifiers gain, the processing and the resetting thresholds and the bias current. View full abstract»

This paper reports on a simulation study of foraging behavior in a 3-D virtual sea snail. The responsible circuit is composed of 8 spiking neurons which is part of a larger 37 neuron brain. The 3-D virtual environment has full soft body physics enabled and is completely defined in software. When no odor targets are available this brain implements a semi-random path foraging behavior and when targe... View full abstract»

Basic emotions correspond to bodily signals. Many psychologists think that there are only a few basic emotions, and that most emotions are combinations of these few. Here we advance a hypothesis that the number of principally different emotions is near infinite. We consider emotions as mental states with hedonic content, indicating satisfaction and dissatisfaction. Our hypothesis is that a large n... View full abstract»

Speech signals convey different types of information which vary from linguistic to speaker-specific and should be used in different tasks. However, it is hard to extract a special type of information such that nearly all acoustic representations of speech present all kinds of information as a whole. The use of the same representation in different tasks creates a difficulty in achieving good perfor... View full abstract»

This paper is focused on developing a model predictive control (MPC) based on recurrent neural network (NN) models. Two regression NN models suitable for prediction purposes are proposed. In order to reduce their computational complexity and to improve their prediction ability, issues related with optimal NN structure (lag space selection, number of hidden nodes), pruning techniques and identifica... View full abstract»