Search results for "Neural"
showing 10 items of 2783 documents
A Fly-Inspired Mushroom Bodies Model for Sensory-Motor Control Through Sequence and Subsequence Learning
2016
Classification and sequence learning are relevant capabilities used by living beings to extract complex information from the environment for behavioral control. The insect world is full of examples where the presentation time of specific stimuli shapes the behavioral response. On the basis of previously developed neural models, inspired by Drosophila melanogaster, a new architecture for classification and sequence learning is here presented under the perspective of the Neural Reuse theory. Classification of relevant input stimuli is performed through resonant neurons, activated by the complex dynamics generated in a lattice of recurrent spiking neurons modeling the insect Mushroom Bodies n…
Sequence Learning in a Single Trial: A Spiking Neurons Model Based on Hippocampal Circuitry.
2020
ABSTRACTIn contrast with our everyday experience using brain circuits, it can take a prohibitively long time to train a computational system to produce the correct sequence of outputs in the presence of a series of inputs. This suggests that something important is missing in the way in which models are trying to reproduce basic cognitive functions. In this work, we introduce a new neuronal network architecture that is able to learn, in a single trial, an arbitrary long sequence of any known objects. The key point of the model is the explicit use of mechanisms and circuitry observed in the hippocampus, which allow the model to reach a level of efficiency and accuracy that, to the best of our…
Moving Learning Machine Towards Fast Real-Time Applications: A High-Speed FPGA-based Implementation of the OS-ELM Training Algorithm
2018
Currently, there are some emerging online learning applications handling data streams in real-time. The On-line Sequential Extreme Learning Machine (OS-ELM) has been successfully used in real-time condition prediction applications because of its good generalization performance at an extreme learning speed, but the number of trainings by a second (training frequency) achieved in these continuous learning applications has to be further reduced. This paper proposes a performance-optimized implementation of the OS-ELM training algorithm when it is applied to real-time applications. In this case, the natural way of feeding the training of the neural network is one-by-one, i.e., training the neur…
Perceptual adaptive insensitivity for support vector machine image coding.
2005
Support vector machine (SVM) learning has been recently proposed for image compression in the frequency domain using a constant epsilon-insensitivity zone by Robinson and Kecman. However, according to the statistical properties of natural images and the properties of human perception, a constant insensitivity makes sense in the spatial domain but it is certainly not a good option in a frequency domain. In fact, in their approach, they made a fixed low-pass assumption as the number of discrete cosine transform (DCT) coefficients to be used in the training was limited. This paper extends the work of Robinson and Kecman by proposing the use of adaptive insensitivity SVMs [2] for image coding u…
Upport vector machines for nonlinear kernel ARMA system identification.
2006
Nonlinear system identification based on support vector machines (SVM) has been usually addressed by means of the standard SVM regression (SVR), which can be seen as an implicit nonlinear autoregressive and moving average (ARMA) model in some reproducing kernel Hilbert space (RKHS). The proposal of this letter is twofold. First, the explicit consideration of an ARMA model in an RKHS (SVM-ARMA 2k) is proposed. We show that stating the ARMA equations in an RKHS leads to solving the regularized normal equations in that RKHS, in terms of the autocorrelation and cross correlation of the (nonlinearly) transformed input and output discrete time processes. Second, a general class of SVM-based syste…
Nonlinear Pulse Shaping in Optical Fibres with a Neural Network
2020
We use a supervised machine-learning model based on a neural network to solve the direct and inverse problems relating to the shaping of optical pulses that occurs upon nonlinear propagation in optical fibres.
SIMULATING THE NUMBER OF ROMANIAN`S PUPILS AND STUDENT USING ARTIFICIAL INTELLIGENCE TECHNIQUES AND COUNTRY`S ECONOMIC ESTATE
2012
The authors present the result of a research that uses artificial neural networks in order to simulate the number of Romanian`s pupils and students (PAS), considering the country`s economic situation. The objective is to determine a better method to forecast the Romanian`s PAS considering its nonlinear behaviour. Also the ANN simulation offers an image about how inputs influence the PAS. In conclusion, the use of the ANN is considered a success and the authors determine the possibility that ANN research application be extended to other countries or even to the European zone.
A Random Neural Network for the Dynamic Multicast Problem
2004
This paper proposes a new heuristic for the dynamic version of the Steiner Tree Problem in Networks (SPN). The heuristic adopts a Random Neural Network (RNN) to improve solutions obtained by previously proposed dynamic algorithms. The Random Neural Network model is adapted to map the intrinsic features of the multicast transmission on a computer network. Exhaustive experiments are carried out to validate the proposed methodology.
Multilayer perceptron neural networks and radial-basis function networks as tools to forecast accumulation of deoxynivalenol in barley seeds contamin…
2011
The capacity of multi-layer perceptron artificial neural networks (MLP-ANN) and radial-basis function networks (RBFNs) to predict deoxynivalenol (DON) accumulation in barley seeds contaminated with Fusarium culmorum under different conditions has been assessed. Temperature (20-28 °C), water activity (0.94-0.98), inoculum size (7-15 mm diameter), and time were the inputs while DON concentration was the output. The dataset was used to train, validate and test many ANNs. Minimizing the mean-square error (MSE) was used to choose the optimal network. Single-layer perceptrons with low number of hidden nodes proved better than double-layer perceptrons, but the performance depended on the training …
Deep CNN for IIF Images Classification in Autoimmune Diagnostics
2019
The diagnosis and monitoring of autoimmune diseases are very important problem in medicine. The most used test for this purpose is the antinuclear antibody (ANA) test. An indirect immunofluorescence (IIF) test performed by Human Epithelial type 2 (HEp-2) cells as substrate antigen is the most common methods to determine ANA. In this paper we present an automatic HEp-2 specimen system based on a convolutional neural network method able to classify IIF images. The system consists of a module for features extraction based on a pre-trained AlexNet network and a classification phase for the cell-pattern association using six support vector machines and a k-nearest neighbors classifier. The class…