scholarly journals Investigation of weight initialization using Fibonacci Sequence on the performance of neural networks*

2021 ◽  
Author(s):  
Dipanwita Sinha Mukherjee ◽  
Naveen Yeri
Keyword(s):  
Neural Network ◽  
Heuristic Method ◽  
Fibonacci Sequence ◽  
Network Models ◽  
Test Accuracy ◽  
Neural Network Models ◽  
Weight Initialization ◽  
And Performance ◽  
Artificial Neural Network Models ◽  
Better Than

<div>Initializing weights are important for fast convergence and performance improvement of Artificial Neural Network models. This study proposes a heuristic method to initialize weights for Neural Network with Fibonacci sequence. Experiments have been carried out with different network structures and datasets and results have been compared with other initialization techniques such as Zero, Random, Xavier and He. It has been observed that for small sized datasets, Fibonacci initialization technique reports 94% of test accuracy which is better than Random (85%) and close to Xavier (93%) and He (96%) initialization methods. Also, for medium sized dataset, we have noted that performance of Fibonacci weight initialization method is comparable with the same for Random, Xavier and He initialization techniques.</div>

scholarly journals Investigation of weight initialization using Fibonacci Sequence on the performance of neural networks*

2021 ◽  
Author(s):  
Dipanwita Sinha Mukherjee ◽  
Naveen Yeri
Keyword(s):  
Neural Network ◽  
Heuristic Method ◽  
Fibonacci Sequence ◽  
Network Models ◽  
Test Accuracy ◽  
Neural Network Models ◽  
Weight Initialization ◽  
And Performance ◽  
Artificial Neural Network Models ◽  
Better Than

<div>Initializing weights are important for fast convergence and performance improvement of Artificial Neural Network models. This study proposes a heuristic method to initialize weights for Neural Network with Fibonacci sequence. Experiments have been carried out with different network structures and datasets and results have been compared with other initialization techniques such as Zero, Random, Xavier and He. It has been observed that for small sized datasets, Fibonacci initialization technique reports 94% of test accuracy which is better than Random (85%) and close to Xavier (93%) and He (96%) initialization methods. Also, for medium sized dataset, we have noted that performance of Fibonacci weight initialization method is comparable with the same for Random, Xavier and He initialization techniques.</div>

scholarly journals Neural network performance based on backpropagation and LVQ as the LoRa RSS fingerprint algorithms for positioning in an open space

2020 ◽  
Vol 8 (2) ◽  
pp. 121-126
Author(s):  
Misbahuddin Misbahuddin ◽  
Muhamad Syamsu Iqbal ◽  
Giri Wahyu Wiriasto ◽  
L Ahmad ◽  
S. Irfan Akbar ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Open Space ◽  
Network Models ◽  
Training Methods ◽  
Neural Network Models ◽  
Artificial Neural ◽  
Artificial Neural Network Models ◽  
Fingerprint Algorithm ◽  
Better Than

Outdoor positioning is one of the important applications in the Internet of things (IoT). The usage of GPS is unsuitable for low-power IoT devices. Alternatively, it can use the LoRa devices. This research aims to find a better method as the fingerprint algorithm for determining the outdoor position using RSS LoRa. The methods used as the fingerprint algorithm were two artificial neural network models, i.e. backpropagation (BP) with four types of training methods and learning vector quantization (LVQ) with two types of training methods. The experiment results show the performance of LVQ1 better than those of LVQ2. Besides, the LVQ1 was also better than the BP method. However, both BP and LVQ2 have a performance that is almost similar to about 70 %. Both of the artificial neural network models, BP and LVQ, can be used as a fingerprint algorithm to determine quite accurate the outdoor object position.

Automatic Electrocardiographic Analysis Using Artificial Neural Network Models

2011 ◽  
Vol 403-408 ◽  
pp. 3587-3593
Author(s):  
T.V.K. Hanumantha Rao ◽  
Saurabh Mishra ◽  
Sudhir Kumar Singh
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Radial Basis Function ◽  
Basis Function ◽  
Network Models ◽  
Neural Network Models ◽  
Radial Basis ◽  
Artificial Neural ◽  
Artificial Neural Network Models ◽  
Self Organizing

In this paper, the artificial neural network method was used for Electrocardiogram (ECG) pattern analysis. The analysis of the ECG can benefit from the wide availability of computing technology as far as features and performances as well. This paper presents some results achieved by carrying out the classification tasks by integrating the most common features of ECG analysis. Four types of ECG patterns were chosen from the MIT-BIH database to be recognized, including normal sinus rhythm, long term atrial fibrillation, sudden cardiac death and congestive heart failure. The R-R interval features were performed as the characteristic representation of the original ECG signals to be fed into the neural network models. Two types of artificial neural network models, SOM (Self- Organizing maps) and RBF (Radial Basis Function) networks were separately trained and tested for ECG pattern recognition and experimental results of the different models have been compared. The trade-off between the time consuming training of artificial neural networks and their performance is also explored. The Radial Basis Function network exhibited the best performance and reached an overall accuracy of 93% and the Kohonen Self- Organizing map network reached an overall accuracy of 87.5%.

scholarly journals Flame Failures and Recovery in Industrial Furnaces: A Neural Network Steady-State Model for the Firing Rate Setpoint Rearrangement

2018 ◽  
Vol 2018 ◽  
pp. 1-15
Author(s):  
Tahmineh Adili ◽  
Zohreh Rostamnezhad ◽  
Ali Chaibakhsh ◽  
Ali Jamali
Keyword(s):  
Neural Network ◽  
Steady State ◽  
Optimization Problems ◽  
Network Models ◽  
Economic Loss ◽  
Neural Network Models ◽  
Firing Rates ◽  
State Models ◽  
Major Equipment ◽  
Artificial Neural Network Models

Burner failures are common abnormal conditions associated with industrial fired heaters. Preventing from economic loss and major equipment damages can be attained by compensating the lost heat due to burners’ failures, which can be possible by defining appropriate setpoints to rearrange the firing rates for healthy burners. In this study, artificial neural network models were developed for estimating the appropriate setpoints for the combustion control system to recover an industrial fired-heater furnace from abnormal conditions. For this purpose, based on an accurate high-order mathematical model, constrained nonlinear optimization problems were solved using the genetic algorithm. For different failure scenarios, the best possible excess firing rates for healthy burners to recover the furnace from abnormal conditions were obtained and data were recorded for training and testing stages. The performances of the developed neural steady-state models were evaluated through simulation experiments. The obtained results indicated the feasibility of the proposed technique to deal with the failures in the combustion system.

Sign in / Sign up

Export Citation Format

Share Document