Neural Networks

The chaotic neural network constructed with chaotic neurons exhibits rich dynamic behaviour with a nonperiodic associative memory. In the chaotic neural network, however, it is difficult to distinguish the stored patterns in the output patterns because ...

The purpose of this manuscript is to propose a method for investigating the global dynamics of nonlinear oscillatory networks, with arbitrary couplings. The procedure is based on the assumption that each oscillator can be accurately described via its ...

Brain overgrowth in early developmental stages of children with autism is well documented. This paper explores the possibility that increases in propagation delays of stimuli and the signals triggered by them, resulting from this overgrowth, may be ...

A digital spiking neuron is a wired system of shift registers and can generate various spike-trains by adjusting the wiring pattern. In this paper we analyze the basic relations between the wiring pattern and characteristics of the spike-train. Based on ...

Currently, there is a lack of general-purpose in-place learning networks that model feature layers in the cortex. By ''general-purpose'' we mean a general yet adaptive high-dimensional function approximator. In-place learning is a biological concept ...

The self-organising map (SOM) and its variant, visualisation induced SOM (ViSOM), have been known to yield similar results to multidimensional scaling (MDS). However, the exact connection has not been established. In this paper, a review on the SOM and ...

A new kernel based contrast function for independent component analysis (ICA) is proposed. This criterion corresponds to a regularized correlation measure in high dimensional feature spaces induced by kernels. The formulation is a multivariate extension ...

We propose a novel framework for performing quantitative Bayesian inference based on qualitative knowledge. Here, we focus on the treatment in the case of inconsistent qualitative knowledge. A hierarchical Bayesian model is proposed for integrating ...

Multi-stage feed-forward neural network (NN) learning with sigmoidal-shaped hidden-node functions is implicitly constrained optimization featuring negative curvature. Our analyses on the Hessian matrix H of the sum-squared-error measure highlight the ...

We perform a deeper analysis of an axiomatic approach to the concept of intrinsic dimension of a dataset proposed by us in the IJCNN'07 paper. The main features of our approach are that a high intrinsic dimension of a dataset reflects the presence of ...

Learning data representations is a fundamental challenge in modeling neural processes and plays an important role in applications such as object recognition. Optimal component analysis (OCA) formulates the problem in the framework of optimization on a ...

We propose a novel similarity measure, called the correntropy coefficient, sensitive to higher order moments of the signal statistics based on a similarity function called the cross-correntopy. Cross-correntropy nonlinearly maps the original time series ...

We propose two strategies to improve the optimization in information geometry. First, a local Euclidean embedding is identified by whitening the tangent space, which leads to an additive parameter update sequence that approximates the geodesic flow to ...

''Wind-up'', a condition related to chronic pain, is a form of plasticity in spinal dorsal horn that can be observed during electrical stimulation of pain receptors at low frequencies (0.3-3 Hz). In this paper, we present a computational model to ...

The relationship between thought and language and, in particular, the issue of whether and how language influences thought is still a matter of fierce debate. Here we consider a discrimination task scenario to study language acquisition in which an ...

Computational models of brain dynamics fall short of performance in speed and robustness of pattern recognition in detecting minute but highly significant pattern fragments. A novel model employs the properties of thermodynamic systems operating far ...

We propose a mechanism to explain both retrospective and prospective recall activity found in experimental data from hippocampal regions CA3 and CA1. Our model of temporal context dependent episodic memory replicates reverse recall in CA1, as recently ...

It is widely acknowledged that categorically organized abstract knowledge plays a significant role in high-order human cognition. Yet, there are many unknown issues about the nature of how categories are internally represented in our mind. Traditionally,...

Many behavioural experiments have pointed out the important role played by the hippocampus in spatial navigation. This role was enlightened by the discovery of hippocampal cells in rodents firing only at very specific locations in an environment, the so-...

I address whether neural networks perform computations in the sense of computability theory and computer science. I explicate and defend the following theses. (1) Many neural networks compute-they perform computations. (2) Some neural networks compute ...

A simple working memory model based on recurrent network activation is proposed and its application to selection and reinforcement of an action is demonstrated as a solution to the temporal credit assignment problem. Reactivation of recent salient cue ...

We designed a VLSI binocular vision system that emulates the disparity computation in the primary visual cortex (V1). The system consists of two silicon retinas, orientation chips, and field programmable gate array (FPGA), mimicking a hierarchical ...

The early visual cortices represent information of several stimulus attributes, such as orientation and color. To understand the coding mechanisms of these attributes in the brain, and the functional organization of the early visual cortices, it is ...

Although sigma-delta modulation is widely used for analog-to-digital (A/D) converters, sigma-delta concepts are only for 1D signals. Signal processing in the digital domain is extremely useful for 2D signals such as used in image processing, medical ...

A powerful symmetrical radial basis function (RBF) aided detector is proposed for nonlinear detection in so-called rank-deficient multiple-antenna assisted beamforming systems. By exploiting the inherent symmetry of the optimal Bayesian detection ...

In this work a new clustering approach is used to explore a well- known dataset [Whitfield, M. L., Sherlock, G., Saldanha, A. J., Murray, J. I., Ball, C. A., Alexander, K. E., et al. (2002). Molecular biology of the cell: Vol. 13. Identification of ...

Modeling neural networks with ordinary differential equations systems is a sensible approach, but also very difficult. This paper describes a new algorithm based on linear genetic programming which can be used to reverse engineer neural networks. The ...

Evaluation of computational intelligence (CI) systems designed to improve the performance of a human operator is complicated by the need to include the effect of human variability. In this paper we consider human (reader) variability in the context of ...