scholarly journals Novel sensitivity method for evaluating the first derivative of the feed-forward neural network outputs

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Ravi Kiran ◽  
Dayakar L. Naik
Keyword(s):  
Neural Network ◽  
Feedforward Neural Network ◽  
Analytical Quality ◽  
Feed Forward Neural Network ◽  
First Derivative ◽  
Network Output ◽  
Novel Method ◽  
Classification Tasks ◽  
Trained Neural Network ◽  
Sensitivity Method

AbstractEvaluating the exact first derivative of a feedforward neural network (FFNN) output with respect to the input feature is pivotal for performing the sensitivity analysis of the trained neural network with respect to the inputs. In this paper, a novel method is presented that computes the analytical quality first derivative of a trained feedforward neural network output with respect to the input features without the need for backpropagation. To this end, the complex step derivative approximation is illustrated, and its implementation in the framework of the feedforward neural network is described. Artificial datasets are generated, and the efficacy of the proposed method for both regression and classification tasks is demonstrated. The results obtained for the regression task indicated that the proposed method is capable of obtaining analytical quality derivatives, and in the case of the classification task, the least relevant features could be identified.

scholarly journals NeurASP: Embracing Neural Networks into Answer Set Programming

2020 ◽  
Author(s):  
Zhun Yang ◽  
Adam Ishay ◽  
Joohyung Lee
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Symbolic Computation ◽  
Answer Set Programming ◽  
Simple Extension ◽  
Symbolic Reasoning ◽  
The Neural Network ◽  
Network Output ◽  
Trained Neural Network ◽  
Answer Set

We present NeurASP, a simple extension of answer set programs by embracing neural networks. By treating the neural network output as the probability distribution over atomic facts in answer set programs, NeurASP provides a simple and effective way to integrate sub-symbolic and symbolic computation. We demonstrate how NeurASP can make use of a pre-trained neural network in symbolic computation and how it can improve the neural network's perception result by applying symbolic reasoning in answer set programming. Also, NeurASP can make use of ASP rules to train a neural network better so that a neural network not only learns from implicit correlations from the data but also from the explicit complex semantic constraints expressed by the rules.

scholarly journals RESTAURANT DENSITY PREDICTION SYSTEM USING FEED FORWARD NEURAL NETWORK

2021 ◽  
Vol 3 (2) ◽  
pp. 127-136
Author(s):  
Muhammad Kurnia Sandi ◽  
Anggunmeka Luhur Prasasti ◽  
Marisa W. Paryasto
Keyword(s):  
Neural Network ◽  
System Analysis ◽  
Modern Society ◽  
Feedforward Neural Network ◽  
Accurate Information ◽  
Simulation Methods ◽  
Prediction System ◽  
Feed Forward Neural Network ◽  
Density Prediction ◽  
Lack Of Information

In this day and age, information about something is so important. The level of trust of modern society depends on the testing of information. Tested and accurate information will have a good impact on the community. One of the important but often missed information is information about the density of a restaurant. Information about restaurant density is important to know because it can affect the actions of someone who will visit the restaurant. This information is also useful to provide information in advance so that diners avoid full restaurants to avoid the spread of the Covid-19 virus, among other things. With limited operating hours as well as the number of restaurant visitors, information about the density of a restaurant becomes much needed. The lack of information on restaurant density is a major problem in the community. The needs of the community, made this study aims to predict the density of a restaurant an hour later. Based on survey data and existing literature data, with simulation methods and also system analysis built using feedforward neural network artificial intelligence architecture and then trained with Backpropagation algorithms produced accuracy of 97.8% with literature data

scholarly journals Classification of Breast Lesions using Modified Masood Score and Neural Network

2018 ◽  
Vol 11 (3) ◽  
pp. 1745-1748
Author(s):  
Sonali Nandish Manoli ◽  
Anand Raj Ulle ◽  
N.M. Nandini ◽  
T.S. Rekha
Keyword(s):  
Neural Network ◽  
Breast Lesion ◽  
Breast Lesions ◽  
Observer Variability ◽  
Feed Forward Neural Network ◽  
Inter Observer Variability ◽  
Class 1 ◽  
Novel Method ◽  
Nuclear Features

In this paper, we propose a novel method to classify Breast Lesions based on minute changes in the cell and nuclear features of the cell. It is important to note these changes as they play a significant role in diagnosis and the line of treatment by an oncologist. To overcome the problem of inter-observer variability the method of scoring is used to grade the lesions considered for the study. We have used the Modified Masood Score and designed an algorithm which classifies a given breast lesion into 6 classes namely Benign, Intermediate class-1,Intermediate class-2, Malignant class-1,Malignant class-2 and Malignant class-3. We have developed a sensitive model using the feed-forward neural network and Pattern Network to achieve the above objective. The Rank of the features is observed using ReliefF Algorithm.

Visualizing the Function Computed by a Feedforward Neural Network

2000 ◽  
Vol 12 (6) ◽  
pp. 1337-1353 ◽  
Author(s):  
Tony A. Plate ◽  
Joel Bert ◽  
John Grace ◽  
Pierre Band
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Statistical Model ◽  
Neural Network Model ◽  
Feedforward Neural Network ◽  
Visualization Method ◽  
Output Function ◽  
Input Output ◽  
Probabilistic Classification ◽  
Classification Tasks

A method for visualizing the function computed by a feedforward neural network is presented. It is most suitable for models with continuous inputs and a small number of outputs, where the output function is reasonably smooth, as in regression and probabilistic classification tasks. The visualization makes readily apparent the effects of each input and the way in which the functions deviate from a linear function. The visualization can also assist in identifying interactions in the fitted model. The method uses only the input-output relationship and thus can be applied to any predictive statistical model, including bagged and committee models, which are otherwise difficult to interpret. The visualization method is demonstrated on a neural network model of how the risk of lung cancer is affected by smoking and drinking.

Sign in / Sign up

Export Citation Format

Share Document