scholarly journals A Database for Learning Numbers by Visual Finger Recognition in Developmental Neuro-Robotics

2021 ◽  
Vol 15 ◽  
Author(s):  
Sergio Davies ◽  
Alexandr Lucas ◽  
Carlos Ricolfe-Viala ◽  
Alessandro Di Nuovo
Keyword(s):  
Neural Networks ◽  
Autonomous Agents ◽  
Numerical Cognition ◽  
Developmental Psychology ◽  
Philosophy Of Mathematics ◽  
Humanoid Robots ◽  
The Body ◽  
Number Representation ◽  
Motor Information ◽  
Learning Behaviours

Numerical cognition is a fundamental component of human intelligence that has not been fully understood yet. Indeed, it is a subject of research in many disciplines, e.g., neuroscience, education, cognitive and developmental psychology, philosophy of mathematics, linguistics. In Artificial Intelligence, aspects of numerical cognition have been modelled through neural networks to replicate and analytically study children behaviours. However, artificial models need to incorporate realistic sensory-motor information from the body to fully mimic the children's learning behaviours, e.g., the use of fingers to learn and manipulate numbers. To this end, this article presents a database of images, focused on number representation with fingers using both human and robot hands, which can constitute the base for building new realistic models of numerical cognition in humanoid robots, enabling a grounded learning approach in developmental autonomous agents. The article provides a benchmark analysis of the datasets in the database that are used to train, validate, and test five state-of-the art deep neural networks, which are compared for classification accuracy together with an analysis of the computational requirements of each network. The discussion highlights the trade-off between speed and precision in the detection, which is required for realistic applications in robotics.

scholarly journals Reversing the Manual Digit Bias in Two-Digit Number Comparison

2017 ◽  
Vol 64 (3) ◽  
pp. 191-204 ◽  
Author(s):  
Thomas J. Faulkenberry ◽  
Alexander Cruise ◽  
Samuel Shaki
Keyword(s):  
Numerical Cognition ◽  
Number Line ◽  
Number Representation ◽  
Digit Number ◽  
Computer Mouse ◽  
Number Comparison ◽  
Number Representations ◽  
Mouse Movements ◽  
Embodied Representation ◽  
Fixed Standard

Abstract. Though recent work in numerical cognition has supported a strong tie between numerical and spatial representations (e.g., a mental number line), less is known about such ties in multi-digit number representations. Along this line, Bloechle, Huber, and Moeller (2015) found that pointing positions in two-digit number comparison were biased leftward toward the decade digit. Moreover, this bias was reduced in unit-decade incompatible pairs. In the present study, we tracked computer mouse movements as participants compared two-digit numbers to a fixed standard (55). Similar to Bloechle et al. (2015) , we found that trajectories exhibited a leftward bias that was reduced for unit-decade incompatible comparisons. However, when positions of response labels were reversed, the biases reversed. That is, we found a rightward bias for compatible pairs that was reduced for incompatible pairs. This result calls into question a purely embodied representation of place value structure and instead supports a competition model of two-digit number representation.

scholarly journals Hukum Penggunaan Aplikasi FaceApp dalam Perspektif Hukum Islam

2020 ◽  
Vol 1 (3) ◽  
pp. 484-504
Author(s):  
Muhammad Yusram ◽  
Askar Patahuddin ◽  
Ahmad Risal
Keyword(s):  
Neural Networks ◽  
Content Analysis ◽  
The Body ◽  
Islamic Perspective ◽  
Research Technique ◽  
Library Research ◽  
Physical Form ◽  
Descriptive Qualitative

This study aims to determine the legal use of the FaceApp application in terms of the Qur'an, sunnah, and opinions of the scholars, as well as its relation to the problem of changing God's creation. This study uses descriptive-qualitative with content analysis and library research technique. The results showed that: first, FaceApp is an application that can change face photos using technology in the form of neural networks that automatically produce very realistic facial transformations in photographs. The opinions of the scholars in the matter of changing God's creation are: 1) neutering humans and animals ; 2) changing physical form; 3) make a tattoo on the body; 4) change the religion of God. Second, the legal use of the FaceApp application in an Islamic perspective by the scholars was divided into two: some scholars banned the use of the FaceApp application and others allowed it. Nevertheless, the majority of the scholars chose to forbid it, based on the evidence in the Qur'an and related hadith and the number of violations and harms posed by this application.

scholarly journals Neural networks supporting social evaluation of bodies based on body shape

2018 ◽  
Author(s):  
Inez Greven ◽  
Paul Downing ◽  
Richard Ramsey
Keyword(s):  
Neural Networks ◽  
Body Shape ◽  
Neural Mechanism ◽  
Relevant Information ◽  
The Body ◽  
Social Judgments ◽  
Social Evaluation ◽  
Fmri Experiment ◽  
Socially Relevant ◽  
Social Inferences

Body shape cues inferences regarding personality and health, but the neural processes underpinning such inferences remain poorly understood. Across two fMRI experiments, we test the extent to which neural networks associated with body perception and theory-of-mind (ToM) support social inferences based on body shape. Participants observed obese, muscular, and slim bodies that cued distinct social inferences as pilot experiments revealed. To investigate judgment intentionality, the first fMRI experiment required participants to detect repeat presentations of bodies, whereas in fMRI Experiment 2 participants intentionally formed an impression. Body and ToM networks were localized using independent functional localisers. Experiment 1 revealed no differential network engagement for muscular or obese compared to slim bodies. By contrast, in Experiment 2, compared to slim bodies, forming impressions of muscular bodies engaged the body-network more, whereas the ToM-network was engaged more when forming impressions of obese bodies. These results demonstrate that social judgments based on body shape do not rely on a single neural mechanism, but rather on multiple mechanisms that are separately sensitive to body fat and muscularity. Moreover, dissociable responses are only apparent when intentionally forming an impression. Thus, these experiments show how segregated networks operate to extract socially-relevant information cued by body shape.

Application of various optimization methods in calculating the error of a neural network for diagnosing parasitological diseases of the gastrointestinal tract

2021 ◽  
Author(s):  
N.T. Abdullaev ◽  
U.N. Musevi ◽  
K.S. Pashaeva
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Gastrointestinal Tract ◽  
Optimization Methods ◽  
Optimization Method ◽  
Medical Diagnostics ◽  
The Body ◽  
Conjugate Gradients ◽  
Practical Significance ◽  
Parasitic Diseases

Formulation of the problem. This work is devoted to the use of artificial neural networks for diagnosing the functional state of the gastrointestinal tract caused by the influence of parasites in the body. For the experiment, 24 symptoms were selected, the number of which can be increased, and 9 most common diseases. The coincidence of neural network diagnostics with classical medical diagnostics for a specific disease is shown. The purpose of the work is to compare the neural networks in terms of their performance after describing the methods of preprocessing, isolating symptoms and classifying parasitic diseases of the gastrointestinal tract. Computer implementation of the experiment was carried out in the NeuroPro 0.25 software environment and optimization methods were chosen for training the network: "gradient descent" modified by Par Tan, "conjugate gradients", BFGS. Results. The results of forecasting using a multilayer perceptron using the above optimization methods are presented. To compare optimization methods, we used the values of the minimum and maximum network errors. Comparison of optimization methods using network errors makes it possible to draw the correct conclusion that for the task at hand, the best results were obtained when using the "conjugate gradients" optimization method. Practical significance. The proposed approach facilitates the work of the experimenter-doctor in choosing the optimization method when working with neural networks for the problem of diagnosing parasitic diseases of the gastrointestinal tract from the point of view of assessing the network error.

Computational Models in Developmental Psychology

2013 ◽  
pp. 476-504
Author(s):  
Thomas R. Shultz
Keyword(s):  
Neural Networks ◽  
Computational Modeling ◽  
Computational Models ◽  
Developmental Psychology ◽  
Probability Distributions ◽  
Network Models ◽  
Developmental Theory ◽  
Negative Evidence ◽  
Developmental Robotics ◽  
Neural Network Models

Computational modeling implements developmental theory in a precise manner, allowing generation, explanation, integration, and prediction. Several modeling techniques are applied to development: symbolic rules, neural networks, dynamic systems, Bayesian processing of probability distributions, developmental robotics, and mathematical analysis. The relative strengths and weaknesses of each approach are identified and examples of each technique are described. Ways in which computational modeling contributes to developmental issues are documented. A probabilistic model of the vocabulary spurt shows that various psychological explanations for it are unnecessary. Constructive neural networks clarify the distinction between learning and development and show how it is possible to escape Fodor’s paradox. Connectionist modeling reveals different versions of innateness and how learning and evolution might interact. Agent-based models analyze the basic principles of evolution in a testable, experimental fashion that generates complete evolutionary records. Challenges posed by stimulus poverty and lack of negative examples are explored in neural-network models that learn morphology or syntax probabilistically from indirect negative evidence.

Optimizing spot welding parameters in a sheet metal assembly by neural networks and genetic algorithm

2007 ◽  
Vol 221 (7) ◽  
pp. 1175-1184 ◽  
Author(s):  
M Hamedi ◽  
M Shariatpanahi ◽  
A Mansourzadeh
Keyword(s):  
Neural Networks ◽  
Spot Welding ◽  
Welding Process ◽  
Welding Current ◽  
The Body ◽  
Welding Parameters ◽  
Automotive Body ◽  
Body In White ◽  
Assembly Operations

Deformation of the spot-welded sub-assemblies in assembly operations and the gap between the matching sub-assemblies have been quality concerns specifically in the automotive industry. Overall quality of the car body and its sub-assemblies, apart from quality of each stamped part, depends markedly on the welding process. This paper considers optimization of three important process parameters in the spot welding of the body components, namely welding current, welding time, and gun force. In this research, first the effects of these parameters on deformation of the sub-assemblies are experimentally investigated. Then neural networks and multi-objective genetic algorithms are utilized to select the optimum values of welding parameters that yield the least values of dimensional deviations in the sub-assemblies. Welding sub-assemblies with the optimized set of parameters brought all of them into the tolerance range. The proposed approach can be utilized in manufacturing sub-assemblies that can fit and match better with adjacent parts in the automotive body. It enhances quality of the joint and will result in improving overall quality of the body in white.

ELECTROCARDIOGRAM ARRHYTHMIA PATTERN RECOGNITION BASED ON AN IMPROVED WAVELET NEURAL NETWORK

2013 ◽  
Vol 13 (01) ◽  
pp. 1350018 ◽  
Author(s):  
GUANGYING YANG
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Pattern Recognition ◽  
Wavelet Neural Network ◽  
The Body ◽  
Support Vector ◽  
Ventricular Premature Beat ◽  
Ecg Signal ◽  
Data Set ◽  
Bundle Branch Block

Electrocardiography (ECG) is a transthoracic interpretation of the electrical activity of the heart over a period of time, as detected by electrodes attached to the outer surface of the skin and recorded by a device external to the body. ECG signal classification is very important for the clinical detection of arrhythmia. This paper presents an application of an improved wavelet neural network structure to the classification of the ECG beats, because of the high precision and fast learning rate. Feature extraction method in this paper is wavelet transform. Our experimental data set is taken from the MIT-BIH arrhythmia database. The correct detection rate of QRS wave is 95% by testing the data of MIT-BIH database. The proposed methods are applied to a large number of ECG signals consisting of 600 training samples and 120 test samples from the MIT-BIH database. The samples equally represent six different ECG signal types, including normal beat, atrial premature beat, ventricular premature beat, left bundle branch block, right bundle branch block and paced beat. In comparison with pattern recognition methods of BP neural networks, RBF neural networks and Support Vector Machines (SVM), the results in this experiment prove that the wavelet neural network method has a better recognition rate when classifying electrocardiogram signals. The experimental results prove that supposed method in this paper is effective for arrhythmia pattern recognition field.

Sign in / Sign up

Export Citation Format

Share Document