Question

The performance of ANN relies heavily on the summation and transformation functions. Explain the combined effects of the summation and transformation functions and how they differ from statistical regression analysis. explain with your own words please

Answer 1

Def:ANN

An artificial neural network is a system of hardware or software that is patterned after the working of neurons in the human brain and nervous system. Artificial neural networks are a variety of deep learning technology which comes under the broad domain of Artificial Intelligence.

Deep learning is a branch of Machine Learning which uses different types of neural networks. These algorithms are inspired by the way our brain functions and therefore many experts believe they are our best shot to moving towards real AI (Artificial Intelligence).

Activities function: like sigmoid,relu , tanh etc

A neural network without an activation function is essentially just a linear regression model. The activation function does the non-linear transformation to the input making it capable to learn and perform more complex tasks.

Activation function decides, whether a neuron should be activated or not by calculating weighted sum and further adding bias with it. The purpose of the activation function is to introduce non-linearity into the output of a neuron.We know, neural network has neurons that work in correspondence of weight, bias and their respective activation function. In a neural network, we would update the weights and biases of the neurons on the basis of the error at the output. This process is known as back-propagation. Activation functions make the back-propagation possible since the gradients are supplied along with the error to update the weights and biases.

Regression and ANn:

I don't think that we can’t say that easily  that model One is better than model Decond. The reality is that in some applications neural networks fits better than another model such as linear regression. And it usually occurs when there are nonlinearities involved. Though, it is important to evaluate before other aspects. For example: a linear reg model will have less parameters to estimate than a NN for a same set of input .variables. Then, a NN will require a larger dataset for its optimization in order to get its benefit of generalization and nonlinear mapping. So, if we do not have enough data, despite of existing nonlinearities involved, a LINEAR reg model may be better adjusted.Regression is method dealing with linear dependencies, neural networks can deal with nonlinearities. So if your data will have some nonlinear dependencies, neural networks should perform better than regression.