Gravity Compensation for Manipulator Control by Neural Networks with Partially Preorganized Structure

1990 ◽  
Vol 2 (4) ◽  
pp. 282-287
Author(s):  
Toshio Tsuji ◽  
◽  
Masataka Nishida ◽  
Toshiaki Takahashi ◽  
Koji Ito
Keyword(s):  
Neural Networks ◽  
Adaptive Learning ◽  
Center Of Mass ◽  
Back Propagation ◽  
Equation Of Motion ◽  
Point Load ◽  
Gravity Compensation ◽  
Error Back Propagation ◽  
Industrial Manipulators ◽  
Parameter Values

The gravity torque of a manipulator can be compensated if the equation of motion can be correctly introduced, but in general industrial manipulators, there are many cases when the parameter values such as the position of center of mass are not clear, and these values largely change by the exchange of hand portions and the grasping of substances. Furthermore, in addition to unclear parameters, there are factors which occur by structural gravity compensation (spring and counter-balance) and which in many cases are difficult to express with the equation of motion. In this paper, compensation of the gravity torque of the manipulator is studied by, the use of neural networks. For this purpose, a model which makes the structure known to be contained in mapping as a unit with preorganized characteristics prepared in parallel with hidden unit of error back propagation-type neural network is proposed, by which the characteristics of the link system which is the object for learning can be imbedded into the network as preorganized knowledge beforehand. Finally, the results of experiments done with the use of industrial manipulators are given, and it is made clear that the compensation of gravity torque of manipulator and adaptive learning for end-point load are possible by the use of this model.

scholarly journals Building robust neural networks using different loss functions

2021 ◽  
pp. 67-82
Author(s):  
Maria Sivak ◽  
◽  
Vladimir Timofeev ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Loss Function ◽  
Back Propagation ◽  
Loss Functions ◽  
Back Propagation Algorithm ◽  
Error Back Propagation ◽  
Propagation Algorithm ◽  
Error Back Propagation Algorithm ◽  
Parameter Values

The paper considers the problem of building robust neural networks using different robust loss functions. Applying such neural networks is reasonably when working with noisy data, and it can serve as an alternative to data preprocessing and to making neural network architecture more complex. In order to work adequately, the error back-propagation algorithm requires a loss function to be continuously or two-times differentiable. According to this requirement, two five robust loss functions were chosen (Andrews, Welsch, Huber, Ramsey and Fair). Using the above-mentioned functions in the error back-propagation algorithm instead of the quadratic one allows obtaining an entirely new class of neural networks. For investigating the properties of the built networks a number of computational experiments were carried out. Different values of outliers’ fraction and various numbers of epochs were considered. The first step included adjusting the obtained neural networks, which lead to choosing such values of internal loss function parameters that resulted in achieving the highest accuracy of a neural network. To determine the ranges of parameter values, a preliminary study was pursued. The results of the first stage allowed giving recommendations on choosing the best parameter values for each of the loss functions under study. The second stage dealt with comparing the investigated robust networks with each other and with the classical one. The analysis of the results shows that using the robust technique leads to a significant increase in neural network accuracy and in a learning rate.

The TP Chromatic Aberration Estimation by Using Neural Networks

2011 ◽  
Vol 121-126 ◽  
pp. 4239-4243 ◽  
Author(s):  
Du Jou Huang ◽  
Yu Ju Chen ◽  
Huang Chu Huang ◽  
Yu An Lin ◽  
Rey Chue Hwang
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Physical Property ◽  
Chromatic Aberration ◽  
Neural Model ◽  
Artificial Intelligent ◽  
Error Back Propagation ◽  
The Neural Networks ◽  
Simulation Results

The chromatic aberration estimations of touch panel (TP) film by using neural networks are presented in this paper. The neural networks with error back-propagation (BP) learning algorithm were used to catch the complex relationship between the chromatic aberration, i.e., L.A.B. values, and the relative parameters of TP decoration film. An artificial intelligent (AI) estimator based on neural model for the estimation of physical property of TP film is expected to be developed. From the simulation results shown, the estimations of chromatic aberration of TP film are very accurate. In other words, such an AI estimator is quite promising and potential in commercial using.

scholarly journals Stellar Image Interpretation System Using Artificial Neural Networks:

10.14311/506 ◽  
2004 ◽  
Vol 44 (1) ◽  
Author(s):  
A. El-Bassuny Alawy ◽  
F. I. Y. Elnagahy ◽  
A. A. Haroon ◽  
Y. A. Azzam ◽  
B. Šimák
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Image Interpretation ◽  
Back Propagation ◽  
Present Approach ◽  
Error Back Propagation ◽  
Polar Function ◽  
Open Star ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

A supervised Artificial Neural Network (ANN) based system is being developed employing the Bi-polar function for identifying stellar images in CCD frames. It is based on feed-forward artificial neural networks with error back-propagation learning. It has been coded in C language. The learning process was performed on a 341 input pattern set, while a similar set was used for testing. The present approach has been applied on a CCD frame of the open star cluster M67. The results obtained have been discussed and compared with those derived in our previous work employing the Uni-polar function and by a package known in the astronomical community (DAOPHOT-II). Full agreement was found between the present approach, that of Elnagahy et al, and the standard astronomical data for the cluster. It has been shown that the developed technique resembles that of the Uni-Polar function, possessing a simple, much faster yet reliable approach. Moreover, neither prior knowledge on, nor initial data from, the frame to be analysed is required, as it is for DAOPHOT-II. 

scholarly journals Modelling an Adaptive Learning System Using Artificial Intelligence

Webology ◽  
2021 ◽  
Vol 19 (1) ◽  
pp. 01-18
Author(s):  
Hayder Rahm Dakheel AL-Fayyadh ◽  
Salam Abdulabbas Ganim Ali ◽  
Dr. Basim Abood
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Adaptive Learning ◽  
Back Propagation ◽  
Learning System ◽  
Spiking Neural Networks ◽  
Domain Specific Language ◽  
Domain Specific ◽  
Adaptive Learning System ◽  
Artificial Neural

The goal of this paper is to use artificial intelligence to build and evaluate an adaptive learning system where we adopt the basic approaches of spiking neural networks as well as artificial neural networks. Spiking neural networks receive increasing attention due to their advantages over traditional artificial neural networks. They have proven to be energy efficient, biological plausible, and up to 105 times faster if they are simulated on analogue traditional learning systems. Artificial neural network libraries use computational graphs as a pervasive representation, however, spiking models remain heterogeneous and difficult to train. Using the artificial intelligence deductive method, the paper posits two hypotheses that examines whether 1) there exists a common representation for both neural networks paradigms for tutorial mentoring, and whether 2) spiking and non-spiking models can learn a simple recognition task for learning activities for adaptive learning. The first hypothesis is confirmed by specifying and implementing a domain-specific language that generates semantically similar spiking and non-spiking neural networks for tutorial mentoring. Through three classification experiments, the second hypothesis is shown to hold for non-spiking models, but cannot be proven for the spiking models. The paper contributes three findings: 1) a domain-specific language for modelling neural network topologies in adaptive tutorial mentoring for students, 2) a preliminary model for generalizable learning through back-propagation in spiking neural networks for learning activities for students also represented in results section, and 3) a method for transferring optimised non-spiking parameters to spiking neural networks has also been developed for adaptive learning system. The latter contribution is promising because the vast machine learning literature can spill-over to the emerging field of spiking neural networks and adaptive learning computing. Future work includes improving the back-propagation model, exploring time-dependent models for learning, and adding support for adaptive learning systems.

KINK FINDING IN THE ALEPH TPC USING NEURAL NETWORKS

1993 ◽  
Vol 08 (29) ◽  
pp. 2715-2727 ◽  
Author(s):  
GEORG STIMPFL-ABELE
Keyword(s):  
Neural Networks ◽  
Back Propagation ◽  
Simulated Data ◽  
Radial Position ◽  
Neural Net ◽  
Decay Vertex ◽  
Feed Forward ◽  
Error Back Propagation ◽  
Conventional Methods ◽  
Tracking Device

The task of finding the decays of charged tracks inside a tracking device is divided into two parts. First a neural net is used to recognize kinks in well-reconstructed tracks. If a kink has been found, a second net determines the radial position of the decay vertex. Both algorithms use feed-forward nets with error back-propagation. Very good performance is obtained in comparison with conventional methods using simulated data from the ALEPH TPC. The behavior of the nets is analyzed by studying the correlations between the inputs and the output.

Neural Network Circuits for Embedded Sensors Applications

2011 ◽  
pp. 276-294
Author(s):  
N. Medrano ◽  
G. Zatorre ◽  
M. T. Sanz ◽  
B. Calvo ◽  
S. Celma
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Ad Hoc ◽  
Low Cost ◽  
Back Propagation ◽  
Cmos Technology ◽  
Error Back Propagation ◽  
Digital Electronics ◽  
Low Sensitivity ◽  
Selection Of

This chapter presents the suitability, development and implementation of programmable analogue artificial neural networks for sensor conditioning in embedded systems. Comments on the use of analogue instead of digital electronics due to the size and power constraints of these applications are included. Performance of an ad-hoc analogue architecture is evaluated, and its characteristics are analyzed. We will verify its low sensitivity to undesired effects, such as component mismatching, due to the capability of selecting and programming the proper weights for a given task. In addition, a brief discussion is offered on the selection of perturbative algorithms instead of classical error back-propagation techniques for weight tuning. At the end of the chapter, we will show the main characteristics of the proposed arithmetic cells implemented in a low-cost CMOS technology.

Modeling of Cell Deformation Under External Force Using Neural Network

2010 ◽  
Author(s):  
M. T. Ahmadian ◽  
G. R. Vossoughi ◽  
A. A. Abbasi ◽  
P. Raeissi
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Three Dimensional ◽  
Point Load ◽  
Cell Deformation ◽  
Back Propagation Algorithm ◽  
Three Dimensional Model ◽  
Error Back Propagation ◽  
Injection Process ◽  
The Neural Network

Embryogenesis, regeneration and cell differentiation in microbiological entities are influenced by mechanical forces. Therefore, development of mechanical properties of these materials is important. Neural network technique is a useful method which can be used to obtain cell deformation by the means of force-geometric deformation data or vice versa. Prior to insertion in the needle injection process, deformation and geometry of cell under external point-load is a key element to understand the interaction between cell and needle. In this paper the goal is the prediction of cell membrane deformation under a certain force, and to visually estimate the force of indentation on the membrane from membrane geometries. The neural network input and output parameters are associated to a three dimensional model without the assumption of the adherent affects. The neural network is modeled by applying error back propagation algorithm. In order to validate the strength of the developed neural network model, the results are compared with the experimental data on mouse oocyte and mouse embryos that are captured from literature. The results of the modeling match nicely the experimental findings.

Sign in / Sign up

Export Citation Format

Share Document