Evolving Hebbian Learning Rules in Voxel-based Soft Robots

Hebbian Learning ◽

Artificial Agents ◽

Soft Robots ◽

Multiple Timescales ◽

Learning Rules ◽

Better Than

<div>According to Hebbian theory, synaptic plasticity is the ability of neurons to strengthen or weaken the synapses among them in response to stimuli. It plays a fundamental role in the processes of learning and memory of biological neural networks. With plasticity, biological agents can adapt on multiple timescales and outclass artificial agents, the majority of which still rely on static Artificial Neural Network (ANN) controllers. In this work, we focus on Voxel-based Soft Robots (VSRs), a class of simulated artificial agents, composed as aggregations of elastic cubic blocks. We propose a Hebbian ANN controller where every synapse is associated with a Hebbian rule that controls the way the weight is adapted during the VSR lifetime. For a given task and morphology, we optimize the controller for the task of locomotion by evolving, rather than the weights, the parameters of the Hebbian rules. Our results show that the Hebbian controller is comparable, often better than a non-Hebbian baseline and that it is more adaptable to unforeseen damages. We also provide novel insights into the inner workings of plasticity and demonstrate that "true" learning does take place, as the evolved controllers improve over the lifetime and generalize well.</div>

AGCS Technique to Improve the Performance of Neural Networks

Journal of Intelligent Systems ◽

10.1515/jisys-2017-0423 ◽

2019 ◽

Vol 29 (1) ◽

pp. 1235-1245

Author(s):

Kishor Kumar Katha ◽

Suresh Pabboju

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Neural Networks ◽

Cuckoo Search ◽

Overall Performance ◽

Artificial Neural ◽

In The Beginning ◽

Better Than

Abstract In this paper, a fresh method is offered regarding training of particular neural networks. This technique is a combination of the adaptive genetic (AG) and cuckoo search (CS) algorithms, called the AGCS method. The intention of training a particular artificial neural network (ANN) is to obtain the finest weight load. With this protocol, a particular weight is taken into account as feedback, which is optimized by means of the hybrid AGCS protocol. In the beginning, a collection of weights is initialized and the similar miscalculation is discovered. Finally, during training of an ANN, we can easily overcome the training complications involving ANNs and also gain the finest overall performance with training of the ANN. We have implemented the proposed system in MATLAB, and the overall accuracy is about 93%, which is much better than that of the genetic algorithm (86%) and CS (88%) algorithm.

Artificial Neural Network Based shafts surface pressures Analysis

Journal of Physics Conference Series ◽

10.1088/1742-6596/2089/1/012046 ◽

2021 ◽

Vol 2089 (1) ◽

pp. 012046

Author(s):

B V Ramana Murthy ◽

Vuppu Padmakar ◽

B N S M Chandrika ◽

Satya Prasad Lanka

Keyword(s):

Neural Network ◽

Neural System ◽

Scientific Model ◽

System Models ◽

Learning Rules ◽

Artificial Neural ◽

Forecast Quality

Abstract This paper exhibits a development of an Artificial Neural Network (ANN) as an instrument for investigation of various parameters of a framework. ANN comprises of various layers of straightforward handling components called as neurons. The neuron performs two capacities, to be specific, assortment of sources of info and age of a yield. Utilization of ANN gives diagram of the hypothesis, learning rules, and uses of the most significant neural system models, definitions and style of Computation. The scientific model of system illuminates the idea of sources of info, loads, adding capacity, actuation work and yields. At that point ANN chooses the sort of learning for modification of loads with change in parameters. At long last the examination of a framework is finished by ANN execution and ANN preparing and forecast quality.

Applications of Artificial Neural Networks for Nonlinear Data - Advances in Computational Intelligence and Robotics ◽

Fundamental Categories of Artificial Neural Networks

10.4018/978-1-7998-4042-8.ch003 ◽

2021 ◽

pp. 30-64

Author(s):

Arunaben Prahladbhai Gurjar ◽

Shitalben Bhagubhai Patel

Keyword(s):

Neural Network ◽

Machine Learning ◽

Neural Networks ◽

Artificial Neural Networks ◽

Mathematical Operation ◽

Artificial Neural ◽

Classification Prediction ◽

Fundamental Categories

The new era of the world uses artificial intelligence (AI) and machine learning. The combination of AI and machine learning is called artificial neural network (ANN). Artificial neural network can be used as hardware or software-based components. Different topology and learning algorithms are used in artificial neural networks. Artificial neural network works similarly to the functionality of the human nervous system. ANN is working as a nonlinear computing model based on activities performed by human brain such as classification, prediction, decision making, visualization just by considering previous experience. ANN is used to solve complex, hard-to-manage problems by accruing knowledge about the environment. There are different types of artificial neural networks available in machine learning. All types of artificial neural networks work based of mathematical operation and require a set of parameters to get results. This chapter gives overview on the various types of neural networks like feed forward, recurrent, feedback, classification-predication.

Fundamental Categories of Artificial Neural Networks

10.4018/978-1-6684-2408-7.ch001 ◽

2022 ◽

pp. 1-30

Author(s):

Arunaben Prahladbhai Gurjar ◽

Shitalben Bhagubhai Patel

Keyword(s):

Neural Network ◽

Machine Learning ◽

Neural Networks ◽

Artificial Neural Networks ◽

Mathematical Operation ◽

Artificial Neural ◽

Classification Prediction ◽

Fundamental Categories

The new era of the world uses artificial intelligence (AI) and machine learning. The combination of AI and machine learning is called artificial neural network (ANN). Artificial neural network can be used as hardware or software-based components. Different topology and learning algorithms are used in artificial neural networks. Artificial neural network works similarly to the functionality of the human nervous system. ANN is working as a nonlinear computing model based on activities performed by human brain such as classification, prediction, decision making, visualization just by considering previous experience. ANN is used to solve complex, hard-to-manage problems by accruing knowledge about the environment. There are different types of artificial neural networks available in machine learning. All types of artificial neural networks work based of mathematical operation and require a set of parameters to get results. This chapter gives overview on the various types of neural networks like feed forward, recurrent, feedback, classification-predication.

Detection and Classification of Power Quality Disturbancewaveform Using MRA Based Modified Wavelet Transfrom and Neural Networks

Journal of Electrical Engineering ◽

10.2478/v10187-010-0033-4 ◽

2010 ◽

Vol 61 (4) ◽

pp. 235-240 ◽

Cited By ~ 5

Author(s):

Perumal Chandrasekar ◽

Vijayarajan Kamaraj

Keyword(s):

Neural Network ◽

Neural Networks ◽

Power Quality ◽

Wavelet Transforms ◽

Back Propagation ◽

Voltage Sag ◽

Artificial Neural ◽

Artificial Neural Network Ann

Detection and Classification of Power Quality Disturbancewaveform Using MRA Based Modified Wavelet Transfrom and Neural Networks In this paper, the modified wavelet based artificial neural network (ANN) is implemented and tested for power signal disturbances. The power signal is decomposed by using modified wavelet transform and the classification is carried by using ANN. Discrete modified wavelet transforms based signal decomposition technique is integrated with the back propagation artificial neural network model is proposed. Varieties of power quality events including voltage sag, swell, momentary interruption, harmonics, transient oscillation and voltage fluctuation are used to test the performance of the proposed approach. The simulation is carried out by using MATLAB software. The simulation results show that the proposed scheme offers superior detection and classification compared to the conventional approaches.

A neural network model for predicting maximum shear capacity of concrete beams without transverse reinforcement

Canadian Journal of Civil Engineering ◽

10.1139/l05-003 ◽

2005 ◽

Vol 32 (4) ◽

pp. 644-657 ◽

Cited By ~ 8

Author(s):

Ayman Ahmed Seleemah

Keyword(s):

Neural Network ◽

Neural Networks ◽

Artificial Neural Networks ◽

Experimental Work ◽

Concrete Beams ◽

Shear Capacity ◽

Transverse Reinforcement ◽

Artificial Neural ◽

Artificial Neural Network Ann

Different relationships have been proposed by codes and researchers for predicting the shear capacity of members without transverse reinforcement. In this paper, the applicability of the artificial neural network (ANN) technique as an analytical alternative to existing methods for predicting this shear capacity is investigated using a critically reviewed and agreed upon database of experimental work that serves as a basis of comparison and (or) assessment of existing and new relationships. Both ANN and eight different codes and researcher's predictions of the shear capacity of the specimens of the database were compared. The ANN predictions are much superior to those of any of the current available relationships.Key words: artificial neural networks, shear capacity, transverse reinforcement, beams.

Investigation of Applying Physics Informed Neural Networks (PINN) and Variants on 2D Aerodynamics Problems

Volume 3: Computational Fluid Dynamics; Micro and Nano Fluid Dynamics ◽

10.1115/fedsm2020-20184 ◽

2020 ◽

Author(s):

Wee-Beng Tay ◽

Murali Damodaran ◽

Zhi-Da Teh ◽

Rahul Halder

Keyword(s):

Neural Network ◽

Neural Networks ◽

Training Data ◽

Batch Size ◽

Test Case ◽

Good Prediction ◽

Time Varying ◽

Artificial Neural ◽

Artificial Neural Network Ann

Abstract Investigation of applying physics informed neural networks on the test case involving flow past Converging-Diverging (CD) Nozzle has been investigated. Both Artificial Neural Network (ANN) and Physics Informed Neural Network (PINN) are used to do the training and prediction. Results show that Artificial Neural Network (ANN) by itself is already able to give relatively good prediction. With the addition of PINN, the error reduces even more, although by only a relatively small amount. This is perhaps due to the already good prediction. The effects of batch size, training iteration and number of epochs on the prediction accuracy have already been tested. It is found that increasing batch size improves the prediction. On the other hand, increasing the training iteration may give poorer prediction due to overfitting. Lastly, in general, increasing epochs reduces the error. More investigations should be done in the future to further reduce the error while at the same time using less training data. More complicated cases with time varying results should also be included. Extrapolation of the results using PINN can also be tested.

Private Label and Macroeconomic Indexes: An Artificial Neural Networks Application

Applied Sciences ◽

10.3390/app10176043 ◽

2020 ◽

Vol 10 (17) ◽

pp. 6043 ◽

Cited By ~ 3

Author(s):

Eloy Gil-Cordero ◽

Juan-Pedro Cabrera-Sánchez

Keyword(s):

Neural Network ◽

Neural Networks ◽

Private Label ◽

Macroeconomic Variables ◽

Macroeconomic Indicators ◽

Per Capita ◽

Artificial Neural ◽

Macroeconomic Indicator

Retail companies operate with a private label assortment of 40–45% of their total assortment, which has led to a significant growth of private labels in recent years in their countries of origin; however, when retail companies decide to internationalize, it is important to know which macroeconomic indicators are more relevant when entering a new country or continent. For that reason, in this study we have as a main objective to establish which are the most transcendental macroeconomic variables for the volume and value of the private label. For this purpose, we have analyzed a total of 1400 samples, creating an artificial neural network (ANN). The results show that the most important macroeconomic indicator that must be taken into consideration above other macroeconomic indicators for retail companies to be successful within a country is the per capita debt. In addition, we have considered in this research that unemployment is not the most important primary indicator for the volume of the private label.

Prediction of Dynamic Impedances Functions Using an Artificial Neural Network (ANN)

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.170-173.3588 ◽

2012 ◽

Vol 170-173 ◽

pp. 3588-3593

Author(s):

Sbartai Badreddine ◽

Kamel Goudjil

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Model ◽

Neural Network Model ◽

Dynamic Properties ◽

Surface Foundation ◽

Artificial Neural ◽

Impedance Functions

Artificial Neural Networks (ANN) has seen an explosion of interest over the last few years. Indeed, anywhere that there are problems of prediction, classification or control, neural networks are being introduced. Hence, the main objective of this paper is to develop a model to predict the response of the soil-structure interaction system without using the calculate code based on sophisticate numerical methods by the employment of a statistical approach based on an Artificial Neural Network model (ANN). In this study, a data base which relates the impedance functions to the geometrics characteristic of the foundation and the dynamic properties of the soil is implemented. This leads to develop a neural network model to predict impedances functions (all modes) of a rectangular surface foundation. Then the results are compared with unused data to check the ANN model’s validity.