|   | 
Details
   web
Records
Author Allende, H.; Salas, R.; Moraga, C.
Title A robust and effective learning algorithm for feedforward neural networks based on the influence function Type
Year 2003 Publication Lecture Notes in Computer Sciences Abbreviated Journal Lect. Notes Comput. Sc.
Volume 2652 Issue Pages 28-36
Keywords feedforward artificial neural networks; robust learning; effective parameter estimate
Abstract The learning process of the Feedforward Artificial Neural Networks relies on the data, though a robustness analysis of the parameter estimates of the model must be done due to the presence of outlying observations in the data. In this paper we seek the robust properties in the parameter estimates in the sense that the influence of aberrant observations or outliers in the estimate is bounded so the neural network is able to model the bulk of data. We also seek a trade off between robustness and efficiency under a Gaussian model. An adaptive learning procedure that seeks both aspects is developed. Finally we show some simulations results applied to the RESEX time series.
Address Univ Tecn Federico Santa Maria, Dept Informat, Valparaiso, Chile, Email: hallende@inf.utfsm.cl
Corporate Author Thesis
Publisher Springer-Verlag Berlin Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN Medium
Area Expedition Conference Pattern Recognition And Image Analysis
Notes WOS:000184832300004 Approved
Call Number UAI @ eduardo.moreno @ Serial 35
Permanent link to this record
 

 
Author Cho, A.D.; Carrasco, R.A.; Ruz, G.A.
Title A RUL Estimation System from Clustered Run-to-Failure Degradation Signals Type
Year 2022 Publication Sensors Abbreviated Journal Sensors
Volume 22 Issue 14 Pages 5323
Keywords prognostics; fault detection; recurrent neural networks; prophet
Abstract The prognostics and health management disciplines provide an efficient solution to improve a system's durability, taking advantage of its lifespan in functionality before a failure appears. Prognostics are performed to estimate the system or subsystem's remaining useful life (RUL). This estimation can be used as a supply in decision-making within maintenance plans and procedures. This work focuses on prognostics by developing a recurrent neural network and a forecasting method called Prophet to measure the performance quality in RUL estimation. We apply this approach to degradation signals, which do not need to be monotonical. Finally, we test our system using data from new generation telescopes in real-world applications.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1424-8220 ISBN Medium
Area Expedition Conference
Notes WOS:000831587200001 Approved
Call Number UAI @ alexi.delcanto @ Serial 1614
Permanent link to this record
 

 
Author Escapil-Inchauspé, P.; Ruz, G.A.
Title Hyper-parameter tuning of physics-informed neural networks: Application to Helmholtz problems Type
Year 2023 Publication Neurocomputing Abbreviated Journal Neurocomputing
Volume 561 Issue Pages 126826
Keywords Physics-informed neural networks; Hyper-parameter optimization; Bayesian optimization; Helmholtz equation
Abstract We consider physics-informed neural networks (PINNs) (Raissiet al., 2019) for forward physical problems. In order to find optimal PINNs configuration, we introduce a hyper-parameter optimization (HPO) procedure via Gaussian processes-based Bayesian optimization. We apply the HPO to Helmholtz equation for bounded domains and conduct a thorough study, focusing on: (i) performance, (ii) the collocation points density r and (iii) the frequency kappa, confirming the applicability and necessity of the method. Numerical experiments are performed in two and three dimensions, including comparison to finite element methods.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0925-2312 ISBN Medium
Area Expedition Conference
Notes WOS:001104342800001 Approved
Call Number UAI @ alexi.delcanto @ Serial 1912
Permanent link to this record
 

 
Author Fernandez, C.; Valle, C.; Saravia, F.; Allende, H.
Title Behavior analysis of neural network ensemble algorithm on a virtual machine cluster Type
Year 2012 Publication Neural Computing & Applications Abbreviated Journal Neural Comput. Appl.
Volume 21 Issue 3 Pages 535-542
Keywords Ensemble learning; Artificial neural networks; Virtualization; Multicore processor; Parallel algorithms
Abstract Ensemble learning has gained considerable attention in different learning tasks including regression, classification, and clustering problems. One of the drawbacks of the ensemble is the high computational cost of training stages. Resampling local negative correlation (RLNC) is a technique that combines two well-known methods to generate ensemble diversity-resampling and error negative correlation-and a fine-grain parallel approach that allows us to achieve a satisfactory balance between accuracy and efficiency. In this paper, we introduce a structure of the virtual machine aimed to test diverse selection strategies of parameters in neural ensemble designs, such as RLNC. We assess the parallel performance of this approach on a virtual machine cluster based on the full virtualization paradigm, using speedup and efficiency as performance metrics, for different numbers of processors and training data sizes.
Address [Fernandez, Cesar; Valle, Carlos; Saravia, Francisco; Allende, Hector] Univ Tecn Federico Santa Maria, Dept Comp Sci, Valparaiso 110 V, Chile, Email: cesferna@inf.utfsm.cl;
Corporate Author Thesis
Publisher Springer Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0941-0643 ISBN Medium
Area Expedition Conference
Notes WOS:000301578900014 Approved
Call Number UAI @ eduardo.moreno @ Serial 251
Permanent link to this record
 

 
Author Goles, E.; Ruz, G.A.
Title Dynamics of neural networks over undirected graphs Type
Year 2015 Publication Neural Networks Abbreviated Journal Neural Netw.
Volume 63 Issue Pages 156-169
Keywords Neural networks; Undirected graphs; Discrete updating schemes; Attractors; Fixed points; Cycles
Abstract In this paper we study the dynamical behavior of neural networks such that their interconnections are the incidence matrix of an undirected finite graph G = (V, E) (i.e., the weights belong to {0, 1}). The network may be updated synchronously (every node is updated at the same time), sequentially (nodes are updated one by one in a prescribed order) or in a block-sequential way (a mixture of the previous schemes). We characterize completely the attractors (fixed points or cycles). More precisely, we establish the convergence to fixed points related to a parameter alpha(G), taking into account the number of loops, edges, vertices as well as the minimum number of edges to remove from E in order to obtain a maximum bipartite graph. Roughly, alpha(G') < 0 for any G' subgraph of G implies the convergence to fixed points. Otherwise, cycles appear. Actually, for very simple networks (majority functions updated in a block-sequential scheme such that each block is of minimum cardinality two) we exhibit cycles with nonpolynomial periods. (C) 2014 Elsevier Ltd. All rights reserved.
Address [Goles, Eric; Ruz, Gonzalo A.] Univ Adolfo Ibanez, Fac Ingn & Ciencias, Santiago, Chile, Email: eric.chacc@uai.cl;
Corporate Author Thesis
Publisher Pergamon-Elsevier Science Ltd Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0893-6080 ISBN Medium
Area Expedition Conference
Notes WOS:000349730800015 Approved
Call Number UAI @ eduardo.moreno @ Serial 460
Permanent link to this record
 

 
Author Henriquez, P.A.; Ruz, G.A.
Title A non-iterative method for pruning hidden neurons in neural networks with random weights Type
Year 2018 Publication Applied Soft Computing Abbreviated Journal Appl. Soft. Comput.
Volume 70 Issue Pages 1109-1121
Keywords Non -iterative learning; Neural networks; Random weights; Garson's algorithm; Pruning; Regression; Classification
Abstract Neural networks with random weights have the advantage of fast computational time in both training and testing. However, one of the main challenges of single layer feedforward neural networks is the selection of the optimal number of neurons in the hidden layer, since few/many neurons lead to problems of underfitting/overfitting. Adapting Garson's algorithm, this paper introduces a new efficient and fast non-iterative algorithm for the selection of neurons in the hidden layer for randomization based neural networks. The proposed approach is divided into three steps: (1) train the network with h hidden neurons, (2) apply Garson's algorithm to the matrix of the hidden layer, and (3) perform pruning reducing hidden layer neurons based on the harmonic mean. Our experiments in regression and classification problems confirmed that the combination of the pruning technique with these types of neural networks improved their predictive performance in terms of mean square error and accuracy. Additionally, we tested our proposed pruning method with neural networks trained under sequential learning algorithms, where Random Vector Functional Link obtained, in general, the best predictive performance compared to online sequential versions of extreme learning machines and single hidden layer neural network with random weights. (C) 2018 Elsevier B.V. All rights reserved.
Address [Henriquez, Pablo A.; Ruz, Gonzalo A.] Univ Adolfo Ibanez, Fac Ingn & Ciencias, Ave Diagonal Las Torres 2640, Santiago, Chile, Email: pabhenriquez@alumnos.uai.cl;
Corporate Author Thesis
Publisher Elsevier Science Bv Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1568-4946 ISBN Medium
Area Expedition Conference
Notes WOS:000443296000077 Approved
Call Number UAI @ eduardo.moreno @ Serial 912
Permanent link to this record
 

 
Author Mora-Rubio, A.; Bravo-Ortiz, M.A.; Quiñones Arredondo, S.; Saborit-Torres, J.M.; Ruz, G.A.; Tabares-Soto, R.
Title Classification of Alzheimers disease stages from magnetic resonance images using deep learning Type
Year 2023 Publication Peer J Computer Science Abbreviated Journal PeerJ Comput. Sci.
Volume 9 Issue Pages e1490
Keywords Computer-aided diagnosis; Convolutional neural networks; Digital image processing; Supervised learning
Abstract Alzheimers disease (AD) is a progressive type of dementia characterized by loss of memory and other cognitive abilities, including speech. Since AD is a progressive disease, detection in the early stages is essential for the appropriate care of the patient throughout its development, going from asymptomatic to a stage known as mild cognitive impairment (MCI), and then progressing to dementia and severe dementia; is worth mentioning that everyone suffers from cognitive impairment to some degree as we age, but the relevant task here is to identify which people are most likely to develop AD. Along with cognitive tests, evaluation of the brain morphology is the primary tool for AD diagnosis, where atrophy and loss of volume of the frontotemporal lobe are common features in patients who suffer from the disease. Regarding medical imaging techniques, magnetic resonance imaging (MRI) scans are one of the methods used by specialists to assess brain morphology. Recently, with the rise of deep learning (DL) and its successful implementation in medical imaging applications, it is of growing interest in the research community to develop computer-aided diagnosis systems that can help physicians to detect this disease, especially in the early stages where macroscopic changes are not so easily identified. This article presents a DL-based approach to classifying MRI scans in the different stages of AD, using a curated set of images from Alzheimer&#65533;s Disease Neuroimaging Initiative and Open Access Series of Imaging Studies databases. Our methodology involves image pre-processing using FreeSurfer, spatial data-augmentation operations, such as rotation, flip, and random zoom during training, and state-of-the-art 3D convolutional neural networks such as EfficientNet, DenseNet, and a custom siamese network, as well as the relatively new approach of vision transformer architecture. With this approach, the best detection percentage among all four architectures was around 89% for AD vs. Control, 80% for Late MCI vs. Control, 66% for MCI vs. Control, and 67% for Early MCI vs. Control.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2376-5992 ISBN Medium
Area Expedition Conference
Notes WOS:001055183700002 Approved
Call Number UAI @ alexi.delcanto @ Serial 1855
Permanent link to this record
 

 
Author Ruz, G.A.; Zuniga, A.; Goles, E.
Title A Boolean network model of bacterial quorum-sensing systems Type
Year 2018 Publication International Journal Of Data Mining And Bioinformatics Abbreviated Journal Int. J. Data Min. Bioinform.
Volume 21 Issue 2 Pages 123-144
Keywords gene regulatory networks; quorum-sensing systems; Boolean networks; neural networks; network inference
Abstract There are several mathematical models to represent gene regulatory networks, one of the simplest is the Boolean network paradigm. In this paper, we reconstruct a regulatory network of bacterial quorum-sensing systems, in particular, we consider Paraburkholderia phytofirmans PsJN which is a plant growth promoting bacteria that produces positive effects in horticultural crops like tomato, potato and grape. To learn the regulatory network from temporal expression pattern of quorum-sensing genes at root plants, we present a methodology that considers the training of perceptrons for each gene and then the integration into one Boolean regulatory network. Using the proposed approach, we were able to infer a regulatory network model whose topology and dynamic exhibited was helpful to gain insight on the quorum-sensing systems regulation mechanism. We compared our results with REVEAL and Best-Fit extension algorithm, showing that the proposed neural network approach obtained a more biologically meaningful network and dynamics, demonstrating the effectiveness of the proposed method.
Address [Ruz, Gonzalo A.; Zuniga, Ana; Goles, Eric] Univ Adolfo Ibanez, Fac Ingn & Ciencias, Av Diagonal Torres 2640, Santiago, Chile, Email: gonzalo.ruz@uai.cl;
Corporate Author Thesis
Publisher Inderscience Enterprises Ltd Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1748-5673 ISBN Medium
Area Expedition Conference
Notes WOS:000451832900003 Approved
Call Number UAI @ eduardo.moreno @ Serial 933
Permanent link to this record
 

 
Author Salas, R.; Allende, H.; Moreno, S.; Saavedra, C.
Title Flexible Architecture of Self Organizing Maps for changing environments Type
Year 2005 Publication Lecture Notes in Computer Sciences Abbreviated Journal Lect. Notes Comput. Sc.
Volume 3773 Issue Pages 642-653
Keywords catastrophic interference; Artificial Neural Networks; Self Organizing Maps; pattern recognition
Abstract Catastrophic Interference is a well known problem of Artificial Neural Networks (ANN) learning algorithms where the ANN forget useful knowledge while learning from new data. Furthermore the structure of most neural models must be chosen in advance. In this paper we introduce a hybrid algorithm called Flexible Architecture of Self Organizing Maps (FASOM) that overcomes the Catastrophic Interference and preserves the topology of Clustered data in changing environments. The model consists in K receptive fields of self organizing maps. Each Receptive Field projects high-dimensional data of the input space onto a neuron position in a low-dimensional output space grid by dynamically adapting its structure to a specific region of the input space. Furthermore the FASOM model automatically finds the number of maps and prototypes needed to successfully adapt to the data. The model has the capability of both growing its structure when novel clusters appears and gradually forgets when the data volume is reduced in its receptive fields. Finally we show the capabilities of our model with experimental results using synthetic sequential data sets and real world data.
Address Univ Valparaiso, Dept Comp, Valparaiso, Chile, Email: rodrigo.salas@uv.cl
Corporate Author Thesis
Publisher Springer-Verlag Berlin Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN Medium
Area Expedition Conference Progress In Pattern Recognition
Notes WOS:000234341500067 Approved
Call Number UAI @ eduardo.moreno @ Serial 44
Permanent link to this record