Showing papers in "Neural Networks in 2005"

TL;DR: In this article, a modified, full gradient version of the LSTM learning algorithm was used for framewise phoneme classification, using the TIMIT database, and the results support the view that contextual information is crucial to speech processing, and suggest that bidirectional networks outperform unidirectional ones.

TL;DR: An appraisal-based emotion theory, the Component Process Model (CPM), is described that seems particularly suited to modeling with the help of artificial neural network approaches, due to its high degree of specificity in postulating underlying mechanisms including efferent physiological and behavioral manifestations.

TL;DR: Three new graph kernels based on the idea of molecular fingerprints and counting labeled paths of depth up to d using depth-first search from each possible vertex are introduced, achieving performances at least comparable, and most often superior, to those previously reported in the literature.

TL;DR: A neural network architecture is constructed to be able to handle the fusion of different modalities (facial features, prosody and lexical content in speech) and results are given and their implications discussed.

TL;DR: A new annotation scheme allowing the annotation of emotion mixtures is presented, and several classification methods are compared to identify relevant emotional states from prosodic, disfluency and lexical cues extracted from the real-life spoken human-human interactions.

TL;DR: The model links data at the cellular level to behavior at the systems level, describing a physiologically plausible mechanism for the brain to recall a given episode which occurred at a specific place and time.

TL;DR: It is shown that the probabilistic structure or context in which events occur is an important predictor of hippocampal activity, and the anterior hippocampus is sensitive to the entropy of a visual stimulus stream.

TL;DR: A novel neurofuzzy system is created, based on rules that have been defined through analysis of FAP variations both at the discrete emotional space, as well as in the 2D continuous activation-evaluation one, that allows for further learning and adaptation to specific users' facial expression characteristics.

TL;DR: In this article, the authors show that combining many models for forecasting gives better estimates than single time series models, and that the combined forecast can underperform significantly compared to its constituents' performances.

TL;DR: Under certain conditions, it is proved that the Cohen-Grossberg neural networks system is exponentially stable globally or convergent globally in finite time.

TL;DR: An engineering control approach to attention is used to model it in a global manner but with relatively sure local foundations at singe neuron level, and the manner in which emotional value can interact with the attention control circuitry is analysed using results of various experimental paradigms.

TL;DR: Two fundamentally different approaches for designing classification models (classifiers) are introduced; the traditional statistical method based on logistic regression and the emerging computationally powerful techniques based on artificial neural networks (ANNs).

TL;DR: There is concern to capture emotion as it occurs in action and interaction as well as in short episodes dominated by emotion, and therefore in a range of contexts, which shape the way it is expressed.

TL;DR: In this article, the dentate and CA3 regions can work together to learn sequences, recall sequences, and generate the phase precession, a phenomenon recorded as a rat moves through place fields, can be interpreted as cued recall of the sequence of upcoming places.

TL;DR: The proposed Generalized 2D Principal Component Analysis (G2DPCA) overcomes the limitations of the recently proposed 2D PCA and shows the excellent performance in face image representation and recognition.

TL;DR: Some of the contributions that modeling emotions in autonomous robots can make towards understanding human emotions-'as sited in the brain' and as used in the authors' interactions with the environment-and emotions in general are discussed.

TL;DR: This paper studies a natural extension of multi-layer perceptrons (MLP) to functional inputs and obtains universal approximation results that show the expressive power of functional MLP is comparable to that of numerical MLP.

TL;DR: In this paper, the authors combine an efficient online spherical k-means (OSKM) algorithm with an existing scalable clustering strategy to achieve fast and adaptive clustering of text streams.

TL;DR: A probably stable learning adaptive control framework with statistical learning of nonlinear functions, and a stability proof including a parameter projection method that is needed to avoid potential singularities during adaptation is presented.

TL;DR: This paper discusses the task of learning a classifier from observed data containing missing values amongst the inputs which are missing completely at random and a non-parametric perspective is adopted by defining a modified risk taking into account the uncertainty of the predicted outputs when missing values are involved.

TL;DR: This paper proposes a new method of recursive blowing-ups which yields the complete desingularization of the reduced rank approximation and gives the exact asymptotic form of its generalization error in Bayesian estimation, based on resolution of learning machine singularities.

TL;DR: It is suggested that the replay phenomenon, in which ensembles of hippocampal neurons replay previously experienced firing sequences during subsequent rest and sleep, may provide practice sequences to improve the speed of TDRL learning, even within a single session.

TL;DR: In this article, an extended version of Incremental Principal Component Analysis (IPCA) and Resource Allocating Network with Long-Term Memory (RAN-LTM) are effectively combined to implement this idea.

TL;DR: The ARTMAP information fusion system uses distributed code representations that exploit the neural network's capacity for one-to-many learning in order to produce self-organizing expert systems that discover hierarchical knowledge structures without any supervised labeling of these relationships.

TL;DR: A model based on the intentional action-perception cycle is proposed to complement the information processing model in multichannel EEGs of rabbits that were trained to respond to conditioned stimuli in visual, auditory and somatic modalities.

TL;DR: Two neural network (NN) applications in the field of biological engineering are developed, designed and parameterized by an evolutionary method based on the evolutionary process of genetic algorithms, which proved to be a powerful tool that can successfully replace the problematic trial-and-error approach.

TL;DR: It is demonstrated that ICA can still be of use by comparing results from four blind subjects with results from one subject without eye bulbs who therefore does not show eye movement artifacts at all.

TL;DR: This paper shows that recognition rate for spontaneous emotionally coloured speech can be improved by using a language model based on increased representation of emotional utterances.

TL;DR: This paper critically evaluates how well the Complementary Learning Systems theory of hippocampo-cortical interactions addresses the stability-plasticity problem and describes a recently developed learning algorithm that leverages neural oscillations to find weak parts of memories and strong competitors and can prevent catastrophic interference in an AB-AC learning paradigm.

TL;DR: Some new conditions ensuring the existence, uniqueness of the equilibrium point and its global exponential stability for cellular neural networks are derived, independent of delays and possess infinitely adjustable real parameters.