scholarly journals Matrix Neo-Fuzzy-System and its Online Learning in Image Recognition Task

2021 ◽  
Vol 24 ◽  
pp. 39-44
Author(s):  
Olha Chala ◽  
Yevgeniy Bodyanskiy
Keyword(s):  
Fuzzy System ◽  
Optimal Algorithm ◽  
Recognition Task ◽  
Neural Systems ◽  
Tuning Parameters ◽  
Online Mode ◽  
Learning Speed ◽  
Computational Implementation ◽  
Time Optimal ◽  
Entropy Criterion

The paper proposes a 2D-hybrid system of computational intelligence, which is based on the generalized neo-fuzzy neuron. The system is characterised by high approximate abilities, simple computational implementation, and high learning speed. The characteristic property of the proposed system is that on its input the signal is fed not in the traditional vector form, but in the image-matrix form. Such an approach allows getting rid of additional convolution-pooling layers that are used in deep neural networks as an encoder. The main elements of the proposed system are a fuzzified multidimensional bilinear model, additional softmax layer, and multidimensional generalized neo-fuzzy neuron tuning with cross-entropy criterion. Compared to deep neural systems, the proposed matrix neo-fuzzy system contains gradually fewer tuning parameters – synaptic weights. The usage of the time-optimal algorithm for tuning synaptic weights allows implementing learning in an online mode.

scholarly journals Fast Probabilistic Neuro-Fuzzy System for Pattern Classification Task

2020 ◽  
Vol 23 ◽  
pp. 12-16
Author(s):  
Yevgeniy Bodyanskiy ◽  
Anastasiia Deineko ◽  
Irina Pliss ◽  
Olha Chala
Keyword(s):  
Fuzzy System ◽  
Probabilistic Neural Network ◽  
Recognition Task ◽  
Training Dataset ◽  
Online Mode ◽  
Neuro Fuzzy ◽  
Computational Implementation ◽  
Processing Information ◽  
Data Points ◽  
Takagi Sugeno

The probabilistic neuro-fuzzy system to solve the image classification-recognition task is proposed. The considered system is a “hybrid” of Specht’s probabilistic neural network and the neuro-fuzzy system of Takagi-Sugeno-Kang. It is designed to solve tasks in case of overlapping classes. Also, it is supposed that the initial data that are fed on the input of the system can be represented in numerical, rank, and nominal (binary) scales. The tuning of the network is implemented with the modified procedure of lazy learning based on the concept “neurons at data points”. Such a learning approach allows substantially reducing the consumption of time and does not require large amounts of training dataset. The proposed system is easy in computational implementation and characterised by a high classification speed, as well as allows processing information both in batch and online mode.

Sequential Time-Optimal Algorithm for Extended Path Tracking Problem

2020 ◽  
Vol 142 (8) ◽  
Author(s):  
Gábor Csorvási ◽  
István Vajk
Keyword(s):  
Degrees Of Freedom ◽  
Optimal Algorithm ◽  
Real Life ◽  
Path Tracking ◽  
Robotic Arm ◽  
Tracking Problem ◽  
Six Degrees Of Freedom ◽  
Time Optimal ◽  
Path Tracking Algorithm ◽  
Extended Path

Abstract This paper presents a fast and easily implementable path tracking algorithm for robots. Usually, for a path tracking problem, the goal is to move the robot on a predefined path, while the joint velocities and accelerations are kept within their limits. This paper deals with the extended case, constraining the forces applied to the objects at the manipulator. First, a problem with a special set of constraints is presented, and a sequential solver method is formulated. The presented sequential solver algorithm has significant computational benefits compared to the direct transcription approach. Then, a practical example is introduced where the proposed algorithm can be applied. At last, the algorithm is validated by real-life experimental results with a six degrees-of-freedom robotic arm.

scholarly journals Channel Density Minimization by Pin Permutation

VLSI Design ◽  
1994 ◽  
Vol 2 (2) ◽  
pp. 171-183
Author(s):  
Yang Cai ◽  
D. F. Wong ◽  
Jason Cong
Keyword(s):  
Optimal Algorithm ◽  
Linear Time ◽  
Layout Design ◽  
Strong Sense ◽  
Np Hard ◽  
Wire Length ◽  
Channel Density ◽  
Time Optimal ◽  
Two Sides ◽  
Intergrated Circuits

We present in this paper a linear time optimal algorithm for minimizing the density of a channel (with exits) by permuting the terminals on the two sides of the channel. This compares favorably with the previously known near-optimal algorithm presented in [6] that runs in superlinear time. Our algorithm has important applications in hierarchical layout design of intergrated circuits. We also show that the problem of minimizing wire length by permuting terminals is NP-hard in the strong sense.

scholarly journals An optimal algorithm for computing all subtree repeats in trees

2014 ◽  
Vol 372 (2016) ◽  
pp. 20130140 ◽  
Author(s):  
T. Flouri ◽  
K. Kobert ◽  
S. P. Pissis ◽  
A. Stamatakis
Keyword(s):  
Optimal Algorithm ◽  
Equivalence Classes ◽  
Tree Structure ◽  
Running Time ◽  
Unrooted Tree ◽  
Time Optimal ◽  
Labelled Trees ◽  
Node Labels

Given a labelled tree T , our goal is to group repeating subtrees of T into equivalence classes with respect to their topologies and the node labels. We present an explicit, simple and time-optimal algorithm for solving this problem for unrooted unordered labelled trees and show that the running time of our method is linear with respect to the size of T . By unordered, we mean that the order of the adjacent nodes (children/neighbours) of any node of T is irrelevant. An unrooted tree T does not have a node that is designated as root and can also be referred to as an undirected tree. We show how the presented algorithm can easily be modified to operate on trees that do not satisfy some or any of the aforementioned assumptions on the tree structure; for instance, how it can be applied to rooted, ordered or unlabelled trees.

Sign in / Sign up

Export Citation Format

Share Document