The purpose of this tutorial is to continue our exploration of regression by constructing linear models with two or more explanatory variables. This is an extension of Lesson 9. I will start with a ...

The purpose of this tutorial is to continue our exploration of multivariate statistics by conducting a simple (one explanatory variable) linear regression analysis. We will continue to use the ...

A linear function approximator is a function y=f(x,w) that is linear in the weights, though not necessarily linear in the input x: Linear function approximators have several nice properties. For ...

Summary In this lesson, we learnt the basics of simple linear regression between two variables as a problem of fitting a straight line to best describe the data associations on a 2-dimensional plane.

In today's deep learning community, three activation functions are commonly used: the sigmoid function, the tanh function and the Rectified Linear Unit, or ReLU for short. When you're building a deep ...

Finding the slope of a linear function is straightforward. Furthermore the slope is the same at each point on the function. However this is not the case with non-linear functions. A non-linear ...

Abstract: Deep Learning is attracting much attention in object recognition and speech processing. A benefit of using the deep learning is that it provides automatic pre-training. Several proposed ...