Skip to content

Ashwin-Dhakal/working-with-300-Dimension-Vectors

Repository files navigation

Neural-Network-for-Question-Duplication-Analysis

artificial neural network model with 86.09 % accuracy Here is the steps carried:

capture capture1 capture2 capture3 capture4 capture5 capture6 capture7

This photo is from the visulaization of initial feature engineering seaborn

Heatmap was generated for calculating degree of effects of input parameter. sea

I know you cant visualize this :D ee

Supervised machine learning model implemented before ANN design:

capture8

This is the summary of neural network:

capture2

Own neural network designed containing 5 hidden layers and 15 input nodes: 36961577_1649855611790400_3100370821776932864_n

Training screenshot:

capture3

Curve plotted:

capture4

Confusion matrix: capture9

UI and Back end development: capture10

And this was the UI designed using Django backend:

capture7 sdfg

results: screencapture-127-0-0-1-8080-searchlist-2018-07-16-12_48_32

Relying on the project's idea, new workflow of architecture of was designed and a research was proposed. You can have a full read of the paper here:
"Exploring Deep Learning in Semantic Question Matching"
https://ieeexplore.ieee.org/document/8586832


Thanks !

About

artificial neural network model with 86.09 % accuracy

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published