scholarly journals A Biologically Plausible Model for Continual Learning using Synaptic Weight Attractors

2021 ◽  
Author(s):  
Romik Ghosh ◽  
Dana Mastrovito ◽  
Stefan Mihalas
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Human Brain ◽  
Synaptic Weight ◽  
The Other ◽  
Biological Mechanisms ◽  
Plausible Model ◽  
Multiple Tasks ◽  
Classification Tasks ◽  
Continual Learning

The human brain readily learns tasks in sequence without forgetting previous ones. Artificial neural networks (ANNs), on the other hand, need to be modified to achieve similar performance. While effective, many algorithms that accomplish this are based on weight importance methods that do not correspond to biological mechanisms. Here we introduce a simple, biologically plausible method for enabling effective continual learning in ANNs. We show that it is possible to learn a weight-dependent plasticity function that prevents catastrophic forgetting over multiple tasks. We highlight the effectiveness of our method by evaluating it on a set of MNIST classification tasks. We further find that the use of our method promotes synaptic multi-modality, similar to that seen in biology.

Ion-gating synaptic transistors with long-term synaptic weight modulation

2021 ◽  
Vol 9 (16) ◽  
pp. 5396-5402
Author(s):  
Youngjun Park ◽  
Min-Kyu Kim ◽  
Jang-Sik Lee
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Synaptic Weight ◽  
Recognition Accuracy ◽  
Artificial Neural ◽  
High Recognition Accuracy

This paper presents synaptic transistors that show long-term synaptic weight modulation via injection of ions. Linear and symmetric weight update is achieved, which enables high recognition accuracy in artificial neural networks.

A Neural Networks Pruning and Data Fusion Based Intrusion Detection Model

2014 ◽  
Vol 651-653 ◽  
pp. 1772-1775
Author(s):  
Wei Gong
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Intrusion Detection ◽  
Data Fusion ◽  
Input Data ◽  
The Other ◽  
Pruning Algorithm ◽  
Detection Model ◽  
Process Ability

The abilities of summarization, learning and self-fitting and inner-parallel computing make artificial neural networks suitable for intrusion detection. On the other hand, data fusion based IDS has been used to solve the problem of distorting rate and failing-to-report rate and improve its performance. However, multi-sensor input-data makes the IDS lose its efficiency. The research of neural network based data fusion IDS tries to combine the strong process ability of neural network with the advantages of data fusion IDS. A neural network is designed to realize the data fusion and intrusion analysis and Pruning algorithm of neural networks is used for filtering information from multi-sensors. In the process of intrusion analysis pruning algorithm of neural networks is used for filtering information from multi-sensors so as to increase its performance and save the bandwidth of networks.

scholarly journals On the Potential of Time Delay Neural Networks to Detect Indirect Coupling between Time Series

Entropy ◽  
2020 ◽  
Vol 22 (5) ◽  
pp. 584
Author(s):  
Riccardo Rossi ◽  
Andrea Murari ◽  
Pasquale Gaudio
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Artificial Neural Networks ◽  
Time Delay ◽  
Causal Relationship ◽  
Gaussian Noise ◽  
The Other ◽  
Causal Relationships ◽  
Indirect Coupling ◽  
Active Research

Determining the coupling between systems remains a topic of active research in the field of complex science. Identifying the proper causal influences in time series can already be very challenging in the trivariate case, particularly when the interactions are non-linear. In this paper, the coupling between three Lorenz systems is investigated with the help of specifically designed artificial neural networks, called time delay neural networks (TDNNs). TDNNs can learn from their previous inputs and are therefore well suited to extract the causal relationship between time series. The performances of the TDNNs tested have always been very positive, showing an excellent capability to identify the correct causal relationships in absence of significant noise. The first tests on the time localization of the mutual influences and the effects of Gaussian noise have also provided very encouraging results. Even if further assessments are necessary, the networks of the proposed architecture have the potential to be a good complement to the other techniques available in the market for the investigation of mutual influences between time series.

Shallow and Deep Artificial Neural Networks for Structural Reliability Analysis

2020 ◽  
Author(s):  
Wellison J. S. Gomes
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Reliability Analysis ◽  
Structural Reliability ◽  
Deep Neural Networks ◽  
Surrogate Models ◽  
The Other ◽  
Computational Costs ◽  
Structural Reliability Analysis ◽  
Artificial Neural

Abstract Surrogate models are efficient tools which have been successfully applied in structural reliability analysis, as an attempt to keep the computational costs acceptable. Among the surrogate models available in the literature, Artificial Neural Networks (ANNs) have been attracting research interest for many years. However, the ANNs used in structural reliability analysis are usually the shallow ones, based on an architecture consisting of neurons organized in three layers, the so-called input, hidden and output layers. On the other hand, with the advent of deep learning, ANNs with one input, one output, and several hidden layers, known as deep neural networks, have been increasingly applied in engineering and other areas. Considering that many recent publications have shown advantages of deep over shallow ANNs, the present paper aims at comparing these types of neural networks in the context of structural reliability. By applying shallow and deep ANNs in the solution of four benchmark structural reliability problems from the literature, employing Monte Carlo simulation and adaptive experimental designs, it is shown that, although good results are obtained for both types of ANNs, deep ANNs usually outperform the shallow ones.

scholarly journals AN ARTIFICIAL NEURAL NETWORKS MODEL FOR THE ESTIMATION OF FORMWORK LABOUR / DIRBTINIŲ NEURONINIŲ TINKLŲ MODELIS, KURIO PASKIRTIS – SKAIČIUOTI KLOJINIAMS SKIRTO DARBO APIMTIS

2011 ◽  
Vol 17 (3) ◽  
pp. 340-347 ◽  
Author(s):  
S. Umit Dikmen ◽  
Murat Sonmez
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Problem Solving ◽  
Human Brain ◽  
Field Measurements ◽  
Reinforced Concrete Frame ◽  
Concrete Frame ◽  
Frame Buildings ◽  
Actual Field ◽  
Artificial Neural

Artificial Neural Networks (ANN) is a problem solving technique imitating the basic working principles of the human brain. The formwork labour cost constitutes an important part within the costs of the reinforced concrete frame buildings. This study suggests a method based on artificial neural networks developed for estimating the required manhours for the formwork activity of such buildings. The introduced method has been verified in the study with reference to the test conducted involving two case studies. In all cases, the model produced results reasonably close to actual field measurements. The model is a simple and quick tool for the estimators and planners to aid them in their work. Santrauka Dirbtiniai neuroniniai tinklai (DNT) – tai problemų sprendimo metodas, imituojantis pagrindinius žmogaus smegenų veiklos principus. Statant gelžbetoninius karkasinius pastatus, nemažą sąnaudų dalį sudaro klojinių ruošimas. Šiame tyrime siūlomas dirbtiniais neuroniniais tinklais pagrįstas metodas, kurio paskirtis – apskaičiuoti, kiek žmogaus darbo valandų reikės ruošti klojinius tokiuose pastatuose. Pristatomas metodas tyrimo metu patikrintas remiantis bandymu, susijusiu su dviem atvejo tyrimais. Visais atvejais modelio pateikti rezultatai buvo gana artimi faktiniams matavimams. Modelis – tai paprastas ir greitai naudojamas įrankis, kuris pravers sąmatininkams ir planuotojams.

scholarly journals ANN analysis in a vision approach for potato inspection

2008 ◽  
Vol 6 (02) ◽  
Author(s):  
R. Rios-Cabrera ◽  
I Lopez-Juarez ◽  
Hsieh Sheng-Jen
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Feature Extraction ◽  
Artificial Neural Networks ◽  
Comparative Analysis ◽  
Physical Properties ◽  
Real Time ◽  
The Other ◽  
Stability And Convergence

An image processing methodology for the extraction of potato properties is explained. The objective is to determine their quality evaluating physical properties and using Artificial Neural Networks (ANN’s) to find misshapen potatoes. A comparative analysis for three connectionist models (Backpropagation, Perceptron and FuzzyARTMAP), evaluating speed and stability for classifying extracted properties is presented. The methodology for image processing and pattern feature extraction is presented together with some results. These results showed that FuzzyARTMAP outperformed the other models due to its stability and convergence speed with times as low as 1 ms per pattern which demonstrates its suitability for real-time inspection. Several algorithms to determine potato defects such as greening, scab, cracks are proposed which can be affectively used for grading different quality of potatoes.

scholarly journals Analisis Jaringan Syaraf Tiruan untuk Memprediksi Jumlah Narapidana pada Lembaga Pemasyarakatan Simalungun dengan Metode Backpropagation

2019 ◽  
Vol 1 ◽  
pp. 762
Author(s):  
Vicky Adriani ◽  
Irfan Sudahri Damanik ◽  
Jaya Tata Hardinata
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Human Brain ◽  
Network Architecture ◽  
Accuracy Rate ◽  
Backpropagation Algorithm ◽  
Artificial Neural ◽  
Detention Facilities

The author has conducted research at the Simalungun District Prosecutor's Office and found the problem of prison rooms that did not match the number of prisoners which caused a lack of security and a lack of detention facilities and risked inmates to flee. Artificial Neural Network which is one of the artificial representations of the human brain that always tries to simulate the learning process of the human brain. The application uses the Backpropagation algorithm where the data entered is the number of prisoners. Then Artificial Neural Networks are formed by determining the number of units per layer. Once formed, training is carried out from the data that has been grouped. Experiments are carried out with a network architecture consisting of input units, hidden units, and output units. Testing using Matlab software. For now, the number of prisoners continues to increase. Predictions with the best accuracy use the 12-3-1 architecture with an accuracy rate of 75% and the lowest level of accuracy using 12-4-1 architecture with an accuracy rate of 25%.

scholarly journals Artificial Neural Networks and Human Brain: Survey of Improvement Possibilities of Learning

2015 ◽  
Vol 3 ◽  
pp. 228 ◽  
Author(s):  
Aleksejs Zorins ◽  
Peteris Grabusts
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Human Brain ◽  
Network Topology ◽  
Hybrid Methods ◽  
Learning Algorithms ◽  
Real Life ◽  
Real Problem ◽  
Brain Functions ◽  
Artificial Neural

<p class="R-AbstractKeywords">There are numerous applications of Artificial Neural Networks (ANN) at the present time and there are different learning algorithms, topologies, hybrid methods etc. It is strongly believed that ANN is built using human brain’s functioning principles but still ANN is very primitive and tricky way for real problem solving. In the recent years modern neurophysiology advanced to a big extent in understanding human brain functions and structure, however, there is a lack of this knowledge application to real ANN learning algorithms. Each learning algorithm and each network topology should be carefully developed to solve more or less complex problem in real life. One may say that almost each serious application requires its own network topology, algorithm and data pre-processing. This article presents a survey of several ways to improve ANN learning possibilities according to human brain structure and functioning, especially one example of this concept – neuroplasticity – automatic adaptation of ANN topology to problem domain.</p>

scholarly journals New Method for Locker Door with Face Security System Using Backpropagation Algorithm

2018 ◽  
Vol 7 (2.13) ◽  
pp. 402
Author(s):  
Y Yusmartato ◽  
Zulkarnain Lubis ◽  
Solly Arza ◽  
Zulfadli Pelawi ◽  
A Armansah ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Pattern Recognition ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Human Brain ◽  
Back Propagation ◽  
The Face ◽  
Artificial Neural ◽  
Hidden Layer

Lockers are one of the facilities that people use to store stuff. Artificial neural networks are computational systems where architecture and operations are inspired by the knowledge of biological neurons in the brain, which is one of the artificial representations of the human brain that always tries to stimulate the learning process of the human brain. One of the utilization of artificial neural network is for pattern recognition. The face of a person must be different but sometimes has a shape similar to the face of others, because the facial pattern is a good pattern to try to be recognized by using artificial neural networks. Pattern recognition on artificial neural network can be done by back propagation method. Back propagation method consists of input layer, hidden layer and output layer.  

Comprehensive Modelling of ANN

2021 ◽  
pp. 18-29
Author(s):  
Meghna Babubhai Patel ◽  
Jagruti N. Patel ◽  
Upasana M. Bhilota
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Information Processing ◽  
Human Brain ◽  
Processing System ◽  
Novel Structure ◽  
Pros And Cons ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Networks Structure

An artificial neural network (ANN) is an information processing modelling of the human brain inspired by the way biological nervous systems behave. There are about 100 billion neurons in the human brain. Each neuron has a connection point between 1,000 and 100,000. The key element of this paradigm is the novel structure of the information processing system. In the human brain, information is stored in such a way as to be distributed, and we can extract more than one piece of this information when necessary from our memory in parallel. We are not mistaken when we say that a human brain is made up of thousands of very powerful parallel processors. It is composed of a large number of highly interconnected processing elements (neurons) working in union to solve specific problems. ANN, like people, learns by example. The chapter includes characteristics of artificial neural networks, structure of ANN, elements of artificial neural networks, pros and cons of ANN.

Sign in / Sign up

Export Citation Format

Share Document