Search results for "NEURAL NETWORK"
showing 10 items of 1385 documents
Exponential Transients in Continuous-Time Symmetric Hopfield Nets
2001
We establish a fundamental result in the theory of continuous-time neural computation, by showing that so called continuous-time symmetric Hopfield nets, whose asymptotic convergence is always guaranteed by the existence of a Liapunov function may, in the worst case, possess a transient period that is exponential in the network size. The result stands in contrast to e.g. the use of such network models in combinatorial optimization applications. peerReviewed
Adaptive Neural Stabilizing Controller for a Class of Mismatched Uncertain Nonlinear Systems by State and Output Feedback
2015
In this paper, first, an adaptive neural network (NN) state-feedback controller for a class of nonlinear systems with mismatched uncertainties is proposed. By using a radial basis function NN (RBFNN), a bound of unknown nonlinear functions is approximated so that no information about the upper bound of mismatched uncertainties is required. Then, an observer-based adaptive controller based on RBFNN is designed to stabilize uncertain nonlinear systems with immeasurable states. The state-feedback and observer-based controllers are based on Lyapunov and strictly positive real-Lyapunov stability theory, respectively, and it is shown that the asymptotic convergence of the closed-loop system to ze…
Adaptive output feedback neural network control of uncertain non-affine systems with unknown control direction
2014
Abstract This paper deals with the problem of adaptive output feedback neural network controller design for a SISO non-affine nonlinear system. Since in practice all system states are not available in output measurement, an observer is designed to estimate these states. In comparison with the existing approaches, the current method does not require any information about the sign of control gain. In order to handle the unknown sign of the control direction, the Nussbaum-type function is utilized. In order to approximate the unknown nonlinear function, neural network is firstly exploited, and then to compensate the approximation error and external disturbance a robustifying term is employed. …
Adaptive neural state-feedback stabilizing controller for nonlinear systems with mismatched uncertainty
2014
In this paper, an adaptive neural network (NN) state-feedback controller for a class of nonlinear systems with mismatched uncertainties is presented. By using a radial basis (RBF) neural network, a bound of unknown nonlinear functions is approximated so that no information about the upper bound of mismatched uncertainties is required. The state-feedback is based on Lyapunov stability theory, and it is shown that the asymptotic convergence of the closed-loop system to zero is achieved while maintaining bounded states at the same time. The presented methods are more general than the previous approaches, handling systems with no restriction on the dimension of the system and the number of inpu…
Region of interest detection using MLP
2014
A novel technique to detect regions of interest in a time series as deviation from the characteristic behavior is proposed. The deterministic form of a signal is obtained using a reliably trained MLP neural network with detailed complexity management and cross-validation based generalization assurance. The proposed technique is demonstrated with simulated and real data. peerReviewed
Quantifying uncertainty in high resolution biophysical variable retrieval with machine learning
2022
The estimation of biophysical variables is at the core of remote sensing science, allowing a close monitoring of crops and forests. Deriving temporally resolved and spatially explicit maps of parameters of interest has been the subject of intense research. However, deriving products from optical sensors is typically hampered by cloud contamination and the trade-off between spatial and temporal resolutions. In this work we rely on the HIghly Scalable Temporal Adaptive Reflectance Fusion Model (HISTARFM) algorithm to generate long gap-free time series of Landsat surface reflectance data by fusing MODIS and Landsat reflectances. An artificial neural network is trained on PROSAIL inversion to p…
A Tour of Learned Static Sorted Sets Dictionaries: From Specific to Generic with an Experimental Performance Analysis
2022
In recent years, in the era of Big Data, studying new methods to improve the performance of well-known procedures, such as searching in a Sorted Set, has become crucial in many fields. A new trend emerging in this scenario combines Machine Learning models with Data Structures, generating the so-called Learned Data Structures. In this thesis, we provide an in-depth experimental study of the use of these models, starting from some evidence known to experts in the field but not experimentally investigated concerning the use of very complex models such as Neural Networks. Then, we document a time/space trade-off scenario that is very important for practitioners and designers users. Furthermore,…
On the Suitability of Neural Networks as Building Blocks for the Design of Efficient Learned Indexes
2022
With the aim of obtaining time/space improvements in classic Data Structures, an emerging trend is to combine Machine Learning techniques with the ones proper of Data Structures. This new area goes under the name of Learned Data Structures. The motivation for its study is a perceived change of paradigm in Computer Architectures that would favour the use of Graphics Processing Units and Tensor Processing Units over conventional Central Processing Units. In turn, that would favour the use of Neural Networks as building blocks of Classic Data Structures. Indeed, Learned Bloom Filters, which are one of the main pillars of Learned Data Structures, make extensive use of Neural Networks to improve…
Non-negative blind source separation techniques for tumor tissue typing using HR-MAS signals.
2010
Given High Resolution Magic Angle Spinning (HR-MAS) signals from several glioblastoma tumor subjects, the goal is to differentiate between tumor tissue types by separating the different sources that contribute to the profile of each spectrum. Blind source separation techniques are applied for obtaining characteristic profiles for necrosis, high cellular tumor and border tumor tissue, and providing the contribution (abundance) of each tumor tissue to the profile of the spectra. The problem is formulated as a non-negative source separation problem. We illustrate the effectiveness of the proposed methods and we analyze to which extent the dimension of the input space could influence the perfor…
A magnetic skyrmion as a non-linear resistive element - a potential building block for reservoir computing
2017
Inspired by the human brain, there is a strong effort to find alternative models of information processing capable of imitating the high energy efficiency of neuromorphic information processing. One possible realization of cognitive computing are reservoir computing networks. These networks are built out of non-linear resistive elements which are recursively connected. We propose that a skyrmion network embedded in frustrated magnetic films may provide a suitable physical implementation for reservoir computing applications. The significant key ingredient of such a network is a two-terminal device with non-linear voltage characteristics originating from single-layer magnetoresistive effects,…