Neural Networks for Regression

website:https://missinglink.ai/guides/neural-network-concepts/neural-networks-regression-part-1-overkill-opportunity/ 

In this article we can learn the concept of regression and Neural Network. After reading this article, we can understand the concept of regression and Neural Network initially.

        Most regression will not perfectly fit the data at hand. if we want to analyze more complex model, applying a Neural Network to the problem can provide much more prediction power compared to a traditional way.

        Regression analysis can show if there is a significant relation between the independent variables, and the strength of the impact. There are seven types of regressions, Linear Regression, Polynomial Regression, Logistics Regression, Stepwise Regression, Ridge Regression, Lasso Regression and ElasticNet Regression.

        Artificial Neural Networks are comprised of simple elements, called neurons and each of them can make simple mathematical decisions. The neurons can analyze complex problems, emulate almost any function including very complex. There are two types of Neural Network, shallow feedforward neural network and deep neural network which have different function to analyze and predict power

        If our regression model perfectly fits our problem, we do not use the Neural Network, but we are modeling complex data set and feel we need more prediction power, we will use neural network. Neural network can automatically construct a prediction function that will eclipse the prediction power of our traditional regression model. Neural Network is more complicated than Regression, but it is vital for us to analyze the complicated model and get better data analysis.