Evolution of fuzzy nearest neighbor neural networks

2002 ◽  
Author(s):  
H. Ishibuchi ◽  
T. Nakashima
Keyword(s):  
Neural Networks ◽  
Nearest Neighbor

scholarly journals RSPCN: Super-Resolution of Digital Elevation Model Based on Recursive Sub-Pixel Convolutional Neural Networks

2021 ◽  
Vol 10 (8) ◽  
pp. 501
Author(s):  
Ruichen Zhang ◽  
Shaofeng Bian ◽  
Houpu Li
Keyword(s):  
Neural Networks ◽  
Digital Elevation Model ◽  
Convolutional Neural Networks ◽  
Adaptive Learning ◽  
Nearest Neighbor ◽  
Super Resolution ◽  
Recursion Theory ◽  
Research Issues ◽  
Digital Elevation ◽  
Elevation Model

The digital elevation model (DEM) is known as one kind of the most significant fundamental geographical data models. The theory, method and application of DEM are hot research issues in geography, especially in geomorphology, hydrology, soil and other related fields. In this paper, we improve the efficient sub-pixel convolutional neural networks (ESPCN) and propose recursive sub-pixel convolutional neural networks (RSPCN) to generate higher-resolution DEMs (HRDEMs) from low-resolution DEMs (LRDEMs). Firstly, the structure of RSPCN is described in detail based on recursion theory. This paper explores the effects of different training datasets, with the self-adaptive learning rate Adam algorithm optimizing the model. Furthermore, the adding-“zero” boundary method is introduced into the RSPCN algorithm as a data preprocessing method, which improves the RSPCN method’s accuracy and convergence. Extensive experiments are conducted to train the method till optimality. Finally, comparisons are made with other traditional interpolation methods, such as bicubic, nearest-neighbor and bilinear methods. The results show that our method has obvious improvements in both accuracy and robustness and further illustrate the feasibility of deep learning methods in the DEM data processing area.

ROBUSTNESS OF COMPLETE STABILITY FOR 1-D CIRCULAR CNNs

2006 ◽  
Vol 16 (08) ◽  
pp. 2177-2190
Author(s):  
MAURO DI MARCO ◽  
CHIARA GHILARDI
Keyword(s):  
Neural Networks ◽  
Equilibrium Point ◽  
Nearest Neighbor ◽  
Perturbation Parameter ◽  
Relative Magnitude ◽  
Loss Of Stability ◽  
Unique Equilibrium ◽  
Small Perturbations ◽  
Structure Preserving ◽  
One Dimensional

This paper investigates the issue of robustness of complete stability of standard Cellular Neural Networks (CNNs) with respect to small perturbations of the nominally symmetric interconnections. More specifically, a class of circular one-dimensional (1-D) CNNs with nearest-neighbor interconnections only, is considered. The class has sparse interconnections and is subject to perturbations which preserve the interconnecting structure. Conditions assuring that the perturbed CNN has a unique equilibrium point at the origin, which is unstable, are provided in terms of relative magnitude of the perturbations with respect to the nominal interconnection weights. These conditions allow one to characterize regions in the perturbation parameter space where there is loss of stability for the perturbed CNN. In turn, this shows that even for sparse interconnections and structure preserving perturbations, robustness of complete stability is not guaranteed in the general case.

scholarly journals Machine Learning–based Analysis of English Lateral Allophones

2019 ◽  
Vol 29 (2) ◽  
pp. 393-405 ◽  
Author(s):  
Magdalena Piotrowska ◽  
Gražina Korvel ◽  
Bożena Kostek ◽  
Tomasz Ciszewski ◽  
Andrzej Cżyzewski
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Nearest Neighbor ◽  
Native Speakers ◽  
Automatic Evaluation ◽  
Classification Methods ◽  
K Nearest Neighbor ◽  
Self Organizing Maps ◽  
Automatic Methods ◽  
Audio Video

Abstract Automatic classification methods, such as artificial neural networks (ANNs), the k-nearest neighbor (kNN) and self-organizing maps (SOMs), are applied to allophone analysis based on recorded speech. A list of 650 words was created for that purpose, containing positionally and/or contextually conditioned allophones. For each word, a group of 16 native and non-native speakers were audio-video recorded, from which seven native speakers’ and phonology experts’ speech was selected for analyses. For the purpose of the present study, a sub-list of 103 words containing the English alveolar lateral phoneme /l/ was compiled. The list includes ‘dark’ (velarized) allophonic realizations (which occur before a consonant or at the end of the word before silence) and 52 ‘clear’ allophonic realizations (which occur before a vowel), as well as voicing variants. The recorded signals were segmented into allophones and parametrized using a set of descriptors, originating from the MPEG 7 standard, plus dedicated time-based parameters as well as modified MFCC features proposed by the authors. Classification methods such as ANNs, the kNN and the SOM were employed to automatically detect the two types of allophones. Various sets of features were tested to achieve the best performance of the automatic methods. In the final experiment, a selected set of features was used for automatic evaluation of the pronunciation of dark /l/ by non-native speakers.

Predictive Modeling Versus Regression

2010 ◽  
pp. 110-152
Author(s):  
Patricia Cerrito
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Discriminant Analysis ◽  
Probability Distribution ◽  
Linear Model ◽  
Predictive Modeling ◽  
Patient Population ◽  
Nearest Neighbor ◽  
General Term ◽  
Outcome Variable

Predictive modeling includes regression, both logistic and linear, depending upon the type of outcome variable. It can also include the generalized linear model. However, there are other types of models also available, including decision trees and artificial neural networks under the general term of predictive modeling. Predictive modeling includes nearest neighbor discriminant analysis, also known as memory based reasoning. These other models are nonparametric and do not require that you know the probability distribution of the underlying patient population. Therefore, they are much more flexible when used to examine patient outcomes. Because predictive modeling uses regression in addition to these other models, the end results will improve upon those found using just regression by itself.

Stability and Hopf Bifurcation of Nearest-Neighbor Coupled Neural Networks With Delays

2020 ◽  
Vol 15 (11) ◽  
Author(s):  
Lu Wang ◽  
Min Xiao ◽  
Shuai Zhou ◽  
Yurong Song ◽  
Jinde Cao
Keyword(s):  
Neural Networks ◽  
Hopf Bifurcation ◽  
Nearest Neighbor ◽  
Multiple Delays ◽  
Dimensional System ◽  
Practical Applications ◽  
Coupled Neural Networks ◽  
The Stability ◽  
Related Characteristic ◽  
Theoretical Analyses

Abstract In this paper, a high-dimensional system of nearest-neighbor coupled neural networks with multiple delays is proposed. Nowadays, most present researches about neural networks have studied the connection between adjacent nodes. However, in practical applications, neural networks are extremely complicated. This paper further considers that there are still connection relationships between nonadjacent nodes, which reflect the intrinsic characteristics of neural networks more accurately because of the complexity of its topology. The influences of multiple delays on the local stability and Hopf bifurcation of the system are explored by selecting the sum of delays as bifurcation parameter and discussing the related characteristic equations. It is found that the dynamic behaviors of the system depend on the critical value of bifurcation. In addition, the conditions that ensure the stability of the system and the criteria of Hopf bifurcation are given. Finally, the correctness of the theoretical analyses is verified by numerical simulation.

SYNCHRONIZATION IN AN ARRAY OF NONLINEARLY COUPLED CHAOTIC NEURAL NETWORKS WITH DELAY COUPLING

2008 ◽  
Vol 18 (10) ◽  
pp. 3101-3111 ◽  
Author(s):  
JIANQUAN LU ◽  
DANIEL W. C. HO ◽  
JINDE CAO
Keyword(s):  
Neural Networks ◽  
Nearest Neighbor ◽  
Chaotic Neural Networks ◽  
Scale Free ◽  
Dynamical Network ◽  
Feedback Strength ◽  
Control Scheme ◽  
Special Cases ◽  
General Complex ◽  
Free Network

A general complex dynamical network consisting of N nonlinearly coupled identical chaotic neural networks with coupling delays is firstly formulated. Many studied models with coupling systems are special cases of this model. Synchronization in such dynamical network is considered. Based on the Lyapunov–Krasovskii stability theorem, some simple controllers with updated feedback strength are introduced to make the network synchronized. The update gain γi can be properly chosen to make some important nodes synchronized quicker or slower than the rest. Two examples including nearest-neighbor coupled networks and scale-free network are given to verify the validity and effectiveness of the proposed control scheme.

Sign in / Sign up

Export Citation Format

Share Document