This is a sequel to my previous blog post where I discussed the fundamental theory of linear regression with gradient descent.

This little work is representative of the early stages of a larger theory being formed from nothing. The components of this thought are related to each other in deep and possibly hidden ways. I sense greater dimensions of depth of the nature of this work which I shall not go into for lack of time.

Here’s the situation: you have a dataset of pairs $(x_i,y_i)$ where $i$ is an indexing variable, assumed to be an integer and $0\le i\le n$ and where $n$ is the total number of datapoints.

Recently as I was reviewing for the ACTs, of the low hanging fruit questions was one that asked to solve for the mean of a set of numbers by hand. Formally, given an n-tuple $x=(x_1,…,x_i,…,x_n)$, I needed to solve for

A few days ago I was met with the task of producing static dashboards for providing a visual overview of some calcium fluorescence data corresponding to neural electrical potenital in 120 C Elegans neurons.

Recently from one of my mailing lists I was presented with the classic problem of solving for how a farmer with a goat, fox and cabbage best transport them all across a river without leaving any predator alone with its prey. You may have head this problem as one of its variants, but the main idas come through. .