In recent work, we introduced nonlinear adaptive activation function (FAN) artificial neuron models, which learn their activation functions in an unsupervised way by information-theoretic adapting rules. We also applied networks of these neurons to some blind signal processing problems, such as independent component analysis and blind deconvolution. The aim of this letter is to study some funda...

Foreign exchange rate is a chaotic time series which is consistent with the MackeyGlass equation. Fuzzy logic is an intelligent computational technique and has good potential in forecasting time-series data. This study uses fuzzy logic to study data of exchange rates and build a dynamic adaptive neuron-fuzzy logic forecasting model. The performance of the model built is compared with an autoreg...

In redundant neural networks, many different combinations of connection weights will produce the same output, thereby providing many possible solutions for a given computation. In this issue of Neuron, Rokni et al. propose that the arm movement representations in the cerebral cortex act like redundant networks that drift randomly between different synaptic configurations with equivalent input-o...

The aim of the present Letter is to introduce a new blind deconvolution algorithm based on fixed-point optimization of a ‘Bussgang’-type cost function. The cost function relies on approximate Bayesian estimation achieved by an adaptive neuron. The main feature of the presented algorithm is fast convergence that guarantees good deconvolution performances with limited computational demand compare...

A FitzHugh–Nagumo type spiking neuron model equipped with an asymmetric activation function is investigated. An analogue nonlinear electrical circuit imitating the dynamics of the model is proposed. It is demonstrated that a simple first order linear filter coupled to the system can inhibit spiking and stabilize the system on an unstable steady state, the position of which is not required to be...

A fuzzy neural network and its relevant fuzzy neuron and fuzzy learning algorithm are introduced. An object-oriented implementation of fuzzy neural network in MATLAB environment is realized. Simulations are carried out by SIMULINK. The performance of fuzzy neural network is experimentally compared with other neural networks trained by backpropagation algorithms. It shows better convergence spee...

A class of data-reusing learning algorithms for real-time recurrent neural networks (RNNs) is analyzed. The analysis is undertaken for a general sigmoid nonlinear activation function of a neuron for the real time recurrent learning training algorithm. Error bounds and convergence conditions for such data-reusing algorithms are provided for both contractive and expansive activation functions. Th...

This paper presents a set of classes we have developed in order to implement adaptive animal behaviours in simulated robots. The programmable learning artificial neural circuits (PLANCS) merge an emulation of the classic behaviour based subsumption architecture with a neuron based circuit interface for cognitive modeling. A number of experiments are presented to exemplify the use of PLANCS in i...