Fundamentals of Deep Learning -Neural Networks

Deep Learning, many of us using this tool to solve the most complicated problems even without understanding it. Tensorflow framework and Keras Interface makes life easy for everyone. But it is necessary to know the basic concepts of Neural Networks to make your solutions more precise. Let me share my understandings.

Why Neural Networks are important?

Imagine that we have a problem, the bank gave all of the transaction details such as customer name, age, bank balance, retired or not, transactions and so on. And asks us to build a model which can predict the Number of Transactions a customer will make next year. Problems seem very simple. Many of us would think of a linear Regression to solve this problem.

y = b + w1x1 + w2x2 + w3x3 + ……………………. + wnxn

But, look at this equation of linear regression. The result is the sum of the individual parts. it doesn’t find the interaction between any of the features. To be more clear, linear regression can map the features to results but they cannot find the relationships between features.

This is why Neural Networks are important. Because in many problems features interact with each other in different ways. The neural network has the ability to find these interactions between features.