Deep Learning Log Loss Function Analysis

143 Views Asked by At

Given the set of parameters of a logistic regression model, and a small set of data points, calculate the j^{th} partial derivative of the log-loss function for some j.

What kind of data points could be given here? The formula for the log-loss function I have is l(w,b)= 1/m ∑_(i=1)->m [ln⁡(1+e^(-y_i(w∙x+b)))]

I get that I want to differentiate with respect to the weight w, but I'm just not sure what this type of problem could look like. Some advice would be helpful. Thanks.

1

There are 1 best solutions below

2
On

You are given $(x_i, y_i), i=1, \ldots, m$ where $y_i$'s are either $1$ or $-1$.. These are the data points.

You are trying to build a linear prediction function and determining $w$ and $b$ which minimizes the loss is your desired task.