DEV Community

loading...

ANN Model testing and training Accuracy Using Keras and Tensorflow.

santosh2702s profile image Santosh Kumar ・2 min read

An artificial neuron network (ANN) is a computational model based on the structure and functions of biological neural networks. Information that flows through the network affects the structure of the ANN because a neural network changes - or learns, in a sense - based on that input and output.
ANNs are considered nonlinear statistical data modeling tools where the complex relationships between inputs and outputs are modeled or patterns are found.
The fact that it can actually learn from observing data sets. In this way, ANN is used as a random function approximation tool. These types of tools help estimate the most cost-effective and ideal methods for arriving at solutions while defining computing functions or distributions. ANN takes data samples rather than entire data sets to arrive at solutions, which saves both time and money. ANNs are considered fairly simple mathematical models to enhance existing data analysis technologies.
Using Spyder by Anaconda. You need to install Tensorflow, Theano and Keras libraries in spyder.Keras is built on top of Tensorflow and Theano so these two libraries will be running in back-end.With the help of a dataset which contains record of churn modelling from various countries.

Measuring accuracy of different Models and try to improve it.

Steps to install Keras Tensorflow

Step 1 — Create New Conda Environment
•conda create -n py35 python=3.5 anaconda
Step 2 — Install Spyder in the New Environment
Step 3 — Install the Packages
•conda install theano
•conda install tensorflow
•conda install keras
Step 4 — Run Spyder from the Environment
Step 5 — Test the Packages

Library Used:

•Matplotlib
It is used to perform some graphical
representations.
•Pandas
•Numpy
•sklearn
•keras
•Tensorflow
It is present as backend Environment.

source code of a data set performed in Spyder. https://github.com/santosh2702/ANN-Model-testing-and-training

Discussion (0)

pic
Editor guide