31 July-5 Aug. 2011
Filter Results
-
[Copyright notice]
Publication Year: 2011, Page(s): 1|
PDF (66 KB)
-
[Front cover]
Publication Year: 2011, Page(s): c1|
PDF (255 KB)
-
Conference program
Publication Year: 2011, Page(s):1 - 36|
PDF (382 KB)
-
IJCNN 2011: Schedule grids
Publication Year: 2011, Page(s):v - x|
PDF (265 KB)
-
[Title page]
Publication Year: 2011, Page(s):iii - xxxvi|
PDF (2060 KB)
-
Author index
Publication Year: 2011, Page(s):1 - 13|
PDF (180 KB)
-
Conference papers
Publication Year: 2011, Page(s):1 - 28|
PDF (260 KB)
-
Efficient Levenberg-Marquardt minimization of the cross-entropy error function
Publication Year: 2011, Page(s):1 - 8
Cited by: Papers (1)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»
-
Beyond probabilistic record linkage: Using neural networks and complex features to improve genealogical record linkage
Publication Year: 2011, Page(s):9 - 14
Cited by: Papers (10)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»
-
Fetal electrocardiogram extraction and R-peak detection for fetal heart rate monitoring using artificial neural network and Correlation
Publication Year: 2011, Page(s):15 - 20
Cited by: Papers (4)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»
-
Stochastic analysis of smart home user activities
Publication Year: 2011, Page(s):21 - 23This 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»
-
Robust model predictive control of nonlinear affine systems based on a two-layer recurrent neural network
Publication Year: 2011, Page(s):24 - 29
Cited by: Papers (9)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»
-
B-spline neural network based digital baseband predistorter solution using the inverse of De Boor algorithm
Publication Year: 2011, Page(s):30 - 36In 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 of biological neural networks for hierarchical or temporal pattern clustering, detection and recognition
Publication Year: 2011, Page(s):37 - 44A 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»
-
Network-based learning through particle competition for data clustering
Publication Year: 2011, Page(s):45 - 52Complex 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»
-
Neural-network-based optimal control for a class of nonlinear cdiscrete-time systems with control constraints using the citerative GDHP algorithm
Publication Year: 2011, Page(s):53 - 60
Cited by: Papers (1)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»
-
Optimal control for discrete-time nonlinear systems with unfixed initial state using adaptive dynamic programming
Publication Year: 2011, Page(s):61 - 67
Cited by: Papers (1)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»
-
Topic model with constrainted word burstiness intensities
Publication Year: 2011, Page(s):68 - 74Word 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»
-
Semi-supervised feature extraction with local temporal regularization for EEG classification
Publication Year: 2011, Page(s):75 - 80
Cited by: Papers (3)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»
-
Temporal and rate decoding in spiking neurons with dendrites
Publication Year: 2011, Page(s):81 - 85How 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»
-
Continuous time recurrent neural network designed for KWTA operation
Publication Year: 2011, Page(s):86 - 89The 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»
-
Foraging behavior in a 3-D virtual sea snail having a spiking neural network brain
Publication Year: 2011, Page(s):90 - 94This 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»
-
Emotions of cognitive dissonance
Publication Year: 2011, Page(s):95 - 102
Cited by: Papers (1)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»
-
Exploring speaker-specific characteristics with deep learning
Publication Year: 2011, Page(s):103 - 110
Cited by: Papers (4) | Patents (2)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»
-
Neural networks for model predictive control
Publication Year: 2011, Page(s):111 - 118This 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»