Search results for "NEURAL NETWORK"
showing 10 items of 1385 documents
A Novel Systolic Parallel Hardware Architecture for the FPGA Acceleration of Feedforward Neural Networks
2019
New chips for machine learning applications appear, they are tuned for a specific topology, being efficient by using highly parallel designs at the cost of high power or large complex devices. However, the computational demands of deep neural networks require flexible and efficient hardware architectures able to fit different applications, neural network types, number of inputs, outputs, layers, and units in each layer, making the migration from software to hardware easy. This paper describes novel hardware implementing any feedforward neural network (FFNN): multilayer perceptron, autoencoder, and logistic regression. The architecture admits an arbitrary input and output number, units in la…
Fast Image Restoration Algorithms Based on PDE Models Using Modified Hopfield Neural Network
2010
Two image restoration algorithms based on modified Hop field neural network and variational partial differential equations (PDE) were proposed in our previous work [1, 2]. But the convergence rate of the proposed algorithms was slow. In this paper, we develop a fast update rule based on modified Hop field neural network (MHNN) of continuous state change and two fast image restoration algorithms. Experimental results show that, when compared with the previous algorithms, our proposed algorithms have better performance both in convergence rate and in image restoration quality.
Detection of Hate Speech Spreaders using Convolutional Neural Networks
2021
In this paper we describe a deep learning model based on a Convolutional Neural Network (CNN). The model was developed for the Profiling Hate Speech Spreaders (HSSs) task proposed by PAN 2021 organizers and hosted at the 2021 CLEF Conference. Our approach to the task of classifying an author as HSS or not (nHSS) takes advantage of a CNN based on a single convolutional layer. In this binary classification task, on the tests performed using a 5-fold cross validation, the proposed model reaches a maximum accuracy of 0.80 on the multilingual (i.e., English and Spanish) training set, and a minimum loss value of 0.51 on the same set. As announced by the task organizers, the trained model presente…
Identifying Images with Ladders Using Deep CNN Transfer Learning
2019
Deep Convolutional Neural Networks (CNNs) as well as transfer learning using their pre-trained models often find applications in image classification tasks. In this paper, we explore the utilization of pre-trained CNNs for identifying images containing ladders. We target a particular use case, where an insurance firm, in order to decide the price for workers’ compensation insurance for its client companies, would like to assess the risk involved in their workplace environments. For this, the workplace images provided by the client companies can be utilized and the presence of ladders in such images can be considered as a workplace hazard and therefore an indicator of risk. To this end, we e…
Comparative Study of Several Machine Learning Algorithms for Classification of Unifloral Honeys
2021
Unifloral honeys are highly demanded by honey consumers, especially in Europe. To ensure that a honey belongs to a very appreciated botanical class, the classical methodology is palynological analysis to identify and count pollen grains. Highly trained personnel are needed to perform this task, which complicates the characterization of honey botanical origins. Organoleptic assessment of honey by expert personnel helps to confirm such classification. In this study, the ability of different machine learning (ML) algorithms to correctly classify seven types of Spanish honeys of single botanical origins (rosemary, citrus, lavender, sunflower, eucalyptus, heather and forest honeydew) was investi…
A machine learning approach to determine airport asphalt concrete layer moduli using heavy weight deflectometer data
2021
An integrated approach based on machine learning and data augmentation techniques has been developed in order to predict the stiffness modulus of the asphalt concrete layer of an airport runway, from data acquired with a heavy weight deflectometer (HWD). The predictive model relies on a shallow neural network (SNN) trained with the results of a backcalculation, by means of a data augmentation method and can produce estimations of the stiffness modulus even at runway points not yet sampled. The Bayesian regularization algorithm was used for training of the feedforward backpropagation SNN, and a k-fold cross-validation procedure was implemented for a fair performance evaluation. The testing p…
Using the Hermite Regression Algorithm to Improve the Generalization Capability of a Neural Network
1999
In this paper it is shown that the ability of classification and the ability of approximating a function are correlated to the value (in the training points) of the gradient of the output function learned by the network.
ChemInform Abstract: Antimicrobial Activity Characterization in a Heterogeneous Group of Compounds.
2010
In this work we carry out a study of pattern recognition to detect the microbiological activity in a group of heterogeneous compounds. The structural descriptors utilized are the topological connectivity indexes. The methods followed are stepwise linear discriminant analysis (linear analysis) and artificial neural network (nonlinear analysis). Although both methods are appropriate to differentiate between active and inactive compounds, the artificial neural network is, in this case, more adequate, since it shows in a test set a prediction success of 98%, versus 92% obtained with linear discriminant analysis.
Antimicrobial Activity Characterization in a Heterogeneous Group of Compounds
1998
In this work we carry out a study of pattern recognition to detect the microbiological activity in a group of heterogeneous compounds. The structural descriptors utilized are the topological connectivity indexes. The methods followed are stepwise linear discriminant analysis (linear analysis) and artificial neural network (nonlinear analysis). Although both methods are appropriate to differentiate between active and inactive compounds, the artificial neural network is, in this case, more adequate, since it shows in a test set a prediction success of 98%, versus 92% obtained with linear discriminant analysis.
Spin Glasses on Thin Graphs
1995
In a recent paper we found strong evidence from simulations that the Isingantiferromagnet on ``thin'' random graphs - Feynman diagrams - displayed amean-field spin glass transition. The intrinsic interest of considering such random graphs is that they give mean field results without long range interactions or the drawbacks, arising from boundary problems, of the Bethe lattice. In this paper we reprise the saddle point calculations for the Ising and Potts ferromagnet, antiferromagnet and spin glass on Feynman diagrams. We use standard results from bifurcation theory that enable us to treat an arbitrary number of replicas and any quenched bond distribution. We note the agreement between the f…