This paper introduces a new class of nonlinear adaptive filters, whose structure is based on Hammerstein model. Such filters derive from the functional link filter (FLAF) model, defined by input expansion, which enhances representation signal through projection in higher dimensional space, and subsequent filtering. In particular, two robust FLAF-based architectures are proposed designed ad hoc to tackle nonlinearities acoustic echo cancellation (AEC). The simplest architecture split FLAF,...

The extreme learning machine (ELM) was recently proposed as a unifying framework for different families of algorithms. classical ELM model consists linear combination fixed number nonlinear expansions the input vector. Learning in is hence equivalent to finding optimal weights that minimize error on dataset. update works batch mode, either with explicit feature mappings or implicit defined by kernels. Although an online version has been former, no work done up this point latter, and whether...

Complex-valued neural networks (CVNNs) are a powerful modeling tool for domains where data can be naturally interpreted in terms of complex numbers. However, several analytical properties the domain (such as holomorphicity) make design CVNNs more challenging task than their real counterpart. In this paper, we consider problem flexible activation functions (AFs) domain, i.e., AFs endowed with sufficient degrees freedom to adapt shape given training data. While has received considerable...

Graph convolutional networks (GCNs) are a family of neural network models that perform inference on graph data by interleaving vertexwise operations and message-passing exchanges across nodes. Concerning the latter, two key questions arise: 1) how to design differentiable exchange protocol (e.g., one-hop Laplacian smoothing in original GCN) 2) characterize tradeoff complexity with respect local updates. In this brief, we show state-of-the-art results can be achieved adapting number...

This paper focuses on online learning procedures for locally recurrent neural nets with emphasis multilayer perceptron (MLP) infinite impulse response (IIR) synapses and its variations which include generalized output activation feedback networks (MLN). We propose a new gradient-based procedure called recursive backpropagation (RBP) whose version, causal (CRBP), has some advantages over other methods. CRBP includes as particular cases (BP), temporal BP, Back-Tsoi algorithm (1991) among...

The authors describe the salient features of using a simulated annealing (SA) algorithm in context designing digital filters with coefficient values expressed as sum power two. A procedure for linear phase filter design, this algorithm, is presented and tested, yielding results good those known optimal methods. then applied to design Nyquist filters, optimizing at same time both frequency response intersymbol interference, cascade form finite-impulse-response (FIR) filters. drawback SA that...

Multilayer perceptrons (MLPs) with weight values restricted to powers of two or sums are introduced. In a digital implementation, these neural networks do not need multipliers but only shift registers when computing in forward mode, thus saving chip area and computation time. A learning procedure, based on backpropagation, is presented for such networks. This procedure requires full real arithmetic therefore must be performed offline. Some test cases presented, concerning MLPs hidden layers...

In this paper two novel nonlinear cascade adaptive architectures, here called sandwich models, suitable for the identification of general systems are presented. The proposed architectures rely on combination structural blocks, each one implementing a linear filter or memoryless function. All functions involved in adaptation process based spline and can be easily modified during learning using gradient-based techniques. particular, simple form on-line algorithms is derived. addition, we...

Palmprint verification is one of the most significant and popular approaches for personal authentication due to its high accuracy efficiency. Using deep region interest (ROI) feature extraction models palmprint verification, a novel approach proposed where convolutional neural networks (CNNs) along with transfer learning are exploited. The extracted ROIs fed final system, which composed two modules. These modules (i) pre-trained CNN architecture as extractor (ii) machine classifier. In order...

Graph representation learning has become a ubiquitous component in many scenarios, ranging from social network analysis to energy forecasting smart grids. In several applications, ensuring the fairness of node (or graph) representations with respect some protected attributes is crucial for their correct deployment. Yet, graph deep remains under-explored, few solutions available. particular, tendency similar nodes cluster on real-world graphs (i.e., homophily) can dramatically worsen these...

The L3DAS22 Challenge is aimed at encouraging the development of machine learning strategies for 3D speech enhancement and sound localization detection in office-like environments. This challenge improves extends tasks L3DAS21 edition. We generated a new dataset, which maintains same general characteristics datasets, but with an extended number data points adding constrains that improve baseline model's efficiency overcome major difficulties encountered by participants previous challenge....

In this paper, a new adaptive spline activation function neural network (ASNN) is presented. Due to the ASNN's high representation capabilities, networks with small number of interconnections can be trained solve both pattern recognition and data processing real-time problems. The main idea use Catmull-Rom cubic as neuron's function, which ensures simple structure suitable for software hardware implementation. Experimental results demonstrate improvements in terms generalization capability...

Recently, a new class of nonlinear adaptive filtering architectures has been introduced based on the functional link filter (FLAF) model. Here we focus specifically split FLAF (SFLAF) architecture, which separates adaptation linear and coefficients using two different filters in parallel. This property makes SFLAF well-suited method for problems like acoustic echo cancellation (NAEC), separation tasks brings some performance improvement. Although flexibility is one main features SFLAF,...