Recently, a new learning algorithm for the feedforward neural network named the extreme learning machine (ELM) which can give better performance than traditional tuning-based learning methods for feedforward neural networks in terms of generalization and learning speed has been proposed by Huang et al. In this paper, we first extend the ELM algorithm from the real domain to the complex domain, ...

Feedforward Neural Network (FNN)-based language models estimate the probability of the next word based on the history of the last N words, whereas Recurrent Neural Networks (RNN) perform the same task based only on the last word and some context information that cycles in the network. This paper presents a novel approach, which bridges the gap between these two categories of networks. In partic...

................................................................................................................................................................. 1

The present document is devoted to structural properties of neural population dynamics and especially their differential flatness. Several applications of differential flatness in the present context can be envisioned, among which: trajectory tracking, feedforward to feedback switching, cyclic character, positivity and boundedness.

A feedforward network with homogeneous connectivity cannot transmit quantitative information by one spike volley. In this paper, quantitative information transmission through neural layers connected by Mexican-Hat-type connectivity is examined. It is shown that the intensity of an input signal can be encoded as a size of an active region in a neural layer. c © 2004 Elsevier B.V. All rights rese...

Tight bounds on the approximation rates of nonlinear approximation by variable-basis functions, which include feedforward neural networks, are investigated. The connections with recent results on neural network approximation are discussed.

The definition of t-norms and t-conorms of the class of Hamacher with multilayer feedforward artificial neural networks is achieved in this work. This fact lets to insert fuzzy knowledge into neural network before its training.

A representation of a class of feedforward neural networks in terms of discrete affine wavelet transforms is developed. It is shown that by appropriate grouping of terms, feedforward neural networks with sigmoidal activation functions can be viewed as architectures which implement affine wavelet decompositions of mappings. It is shown that the wavelet transform formalism provides a mathematical...

Building on earlier work extending Sigma’s mixed (symbols + probabilities) graphical band to inference in feedforward neural networks, two forms of neural network learning – target propagation and backpropagation – are introduced, bringing Sigma closer to a full neural-symbolic architecture. Adapting Sigma’s reinforcement learning (RL) capability to use neural networks in policy learning then y...

Received Jan 3, 2018 Revised Mar 5, 2018 Accepted Mar 23, 2018 Of the many audio features available, this paper focuses on the comparison of two most popular features, i.e. line spectral frequencies (LSF) and MelFrequency Cepstral Coefficients. We trained a feedforward neural network with various hidden layers and number of hidden nodes to identify five different languages, i.e. Arabic, Chinese...