A neural-network model for learning domain rules based on its activation function characteristics

1998 ◽  
Vol 9 (5) ◽  
pp. 787-795 ◽  
Author(s):  
LiMin Fu
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Activation Function

scholarly journals General Recurrent Neural Network for Solving Generalized Linear Matrix Equation

Complexity ◽  
2017 ◽  
Vol 2017 ◽  
pp. 1-7 ◽  
Author(s):  
Zhan Li ◽  
Hong Cheng ◽  
Hongliang Guo
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Recurrent Neural Network ◽  
Neural Network Model ◽  
Matrix Equation ◽  
Activation Function ◽  
Linear Matrix ◽  
Activation Functions ◽  
State Matrix ◽  
Linear Matrix Equation

This brief proposes a general framework of the nonlinear recurrent neural network for solving online the generalized linear matrix equation (GLME) with global convergence property. If the linear activation function is utilized, the neural state matrix of the nonlinear recurrent neural network can globally and exponentially converge to the unique theoretical solution of GLME. Additionally, as compared with the case of using the linear activation function, two specific types of nonlinear activation functions are proposed for the general nonlinear recurrent neural network model to achieve superior convergence. Illustrative examples are shown to demonstrate the efficacy of the general nonlinear recurrent neural network model and its superior convergence when activated by the aforementioned nonlinear activation functions.

The Application of Neural Network in the Bionic Control System of an Artificial Heart Based on Neuroshell

2013 ◽  
Vol 709 ◽  
pp. 862-866
Author(s):  
Teng Jing ◽  
Fang Gun Wang ◽  
Kun Xi Qian
Keyword(s):  
Neural Network ◽  
Control System ◽  
Network Model ◽  
Neural Network Model ◽  
Artificial Heart ◽  
Pressure Head ◽  
Activation Function ◽  
Rotating Speed ◽  
The Neural Network ◽  
Blood Pumps

With the development of heart pumps, more and more commercial artificial heart have been applied to clinic use. However, most of the products produce some discomfort to human body, which coudn’t meet the physiological requirements of patients. Therefore, further improvement and enhancement for these products are needed and adopting bionic control using neural network is an effective method to improve heart pumps’ comfort. A neural network model was established in this paper according to the relationship among the pressure head, the motor power and the rotating speed using using Based on neural network software Neuroshell2. Based on the defined appropriate activation function, a lot of data were studied and trained for optimization of the neural network model and determination of weights and deviations . Finally, the bionic control system was built and the experiments of the control system were conducted. The results reveal that the error measured values and the actual values was within 5% and acceptable and that the bionic control system using neural network is proved to improve the the comfort after implantation of blood pumps.

Periodic oscillation for a complex-valued neural network model with discrete and distributed delays

2020 ◽  
Vol 8 (5) ◽  
Author(s):  
Chunhua Feng
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Sufficient Conditions ◽  
Periodic Oscillation ◽  
Activation Function ◽  
Distributed Delays ◽  
Oscillatory Solutions ◽  
Complex Valued ◽  
Theoretical Results

In this paper, a complex-valued neural network model with discrete and distributed delays is investigated under the assumption that the activation function can be separated into its real and imaginary parts. Based on the mathematical analysis method, some sufficient conditions to guarantee the existence of periodic oscillatory solutions are established. Computer simulation is given to illustrate the validity of the theoretical results.

scholarly journals MoView Engine : An Open Source Movie Recommender

2020 ◽  
Vol 32 ◽  
pp. 03008
Author(s):  
Vallari Manavi ◽  
Anjali Diwate ◽  
Priyanka Korade ◽  
Anita Senathi
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
Human Brain ◽  
Network Model ◽  
Neural Network Model ◽  
Recommendation System ◽  
Activation Function ◽  
End Users ◽  
History Of

Recommendation is an ideology that works as choice-based system for the end users. Users are recommended with their favorite movies based on history of other watched movies or based on the category of the movies. These types of recommendations are becoming popular because of their ability to think and react as human brain. For this purpose, deep learning or artificial intelligence comes into picture. It is the ability to think as a human brain as give the output best suited to the end users liking. This paper focuses on implementing the recommendation system of movies using deep learning with neural network model using the activation function of SoftMax to give an experience to users as friendly recommendation. Moreover, this paper focuses on different scenarios of recommendation like the recommendation based on history, genre of the movie etc.

scholarly journals Tensorized Neural Network for Multi-Aspect Rating-Based Recommendation

2019 ◽  
Vol 8 (2S11) ◽  
pp. 547-551
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Activation Function ◽  
Research Area ◽  
Experimental Result ◽  
Computational Time ◽  
Local Optimum ◽  
Tensor Factorization ◽  
Value Decomposition

Generating personalized recommendations is one of the most crucial aspects in Recommender System research area. Most of the researches only focus on the accuracy of recommendation using collaborative filtering that relies on a single overall rating that represents the overall preferences. However, the user may have a different emphasis on different specific aspects that affect the users’ final rating decisions. Therefore, we present a neural network model that utilize multi-aspects ratings using Tensor Factorization to improve the accuracy of personalization, as well as optimizing the dynamic weights of the aspect. To measure the estimated weights for the aspects, we employ the Higher Order Singular Value Decomposition (HOSVD) technique called CANDECOMP/PARAFAC (CP) decomposition that allows for multi-faceted data processing. We then develop the Neural Network with backpropagation error to train the model with different parameter settings and limited computational time. We also use a non-linear activation function in each hidden layer in various settings. The experimental result measured using MAE shows that the proposed model has significantly outperformed the baseline approach in terms of the prediction accuracy. Based on the observation, the performance of rating prediction has been improved by employing the Tensorized Neural Network model and can overcome the problem of local optimum convergence for multi-aspect rating recommendation.

Neural Network Model to Estimate and Predict Cell Mass Concentration in Lipase Fermentation

2014 ◽  
pp. 303-316
Author(s):  
David K. Daniel ◽  
Vikramaditya Bhandari
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Mass Concentration ◽  
Cell Mass ◽  
Back Propagation ◽  
Activation Function ◽  
Training Data ◽  
Network Configuration ◽  
Cell Mass Concentration

Lipase is an industrially important enzyme with major use in food industries. The demand of lipase is increasing every year. An online prediction of cell mass concentration is of great value in real time process involving the production of lipase. In the current work, the use of a back-propagation multilayer neural network to predict cell mass during lipase production by Rhizopus delemar NRRL 1472 is targeted. Network training data with respect to time is generated by carrying out experiments in laboratory. The fungus is grown in erlenmeyer flasks at initial pH of 5.6, temperature of 30ºC, and at 150 rpm. During the experiments, readings for cell mass growth are collected in specific period of time. By the training data, an artificial neural network model programmed in MATLAB for Windows is trained and used for prediction of cell mass. The Levenberg-Marquardt algorithm with back-propagation is used in the network to get the optimized weights. The optimum network configuration with different activation function and the number of nodes in the hidden layer are identified by trial and error method. Sigmoid unipolar activation function is 2-5-1, whereas logarithmoid and sigmoid bipolar is 2-3-1. These are chosen according to the values of Sum of Square of Errors (SSE), Root Mean Square (RMS) training and testing. The sigmoid unipolar activation function gives a good fit for estimated value with network configuration 2-5-1, which could be used for generalization.

scholarly journals Modeling of Solar Radiation Using the Wavelet Neural Network Model in Mataram City Lombok Island

2020 ◽  
Vol 11 (3) ◽  
pp. 178
Author(s):  
Syamsul Bahri
Keyword(s):  
Neural Network ◽  
Solar Radiation ◽  
Network Model ◽  
Neural Network Model ◽  
Learning Process ◽  
Human Life ◽  
Activation Function ◽  
Wavelet Neural Network ◽  
Neural Network Learning ◽  
The Neural Network

Sunlight is a source of energy for living things in general. In reality, the intensity of solar radiation is an environmental parameter that has positive and negative impacts on human life in particular. Furthermore, the knowledge on the characteristics of solar radiation, including its distribution pattern, is considered by many circles, both policy-makers and researchers in the environmental field. This study aims to create a solar radiation model in response to meteorological factors such as wind speed, air pressure and temperature, humidity, and rainfall using the Wavelet Neural Network (WNN). The modeling of solar radiation in this study is carried out by simultaneously utilizing its advantages as a hybrid model that combines the neural network model and the wavelet method. These advantages through the learning process (supervised learning) are multiplied through the use of the wavelet transform as a pre-processing data method and two type wavelets function, B-spline and Morlet wavelets, as an activation function in the neural network learning process. The WNN model was analyzed in two cases of meteorological variables, which are with and without rainfall. The results based on the root of the mean square error (RMSE) indicator show that the WNN model in these two cases is quite accurate. Meanwhile, the other indicator shows that the interval of the data distribution from the model is within the actual range. This implies that the predicted intensity of the solar radiation will be in a safe position in its adverse effect when the model is used as a reference.

Sign in / Sign up

Export Citation Format

Share Document