Geospatial image segmentation using topographic data and Transfer Learning — Practical examples of semantic image segmentation, which aims to identify features on a pixel-wise basis, range from self-driving cars to detecting ships in satellite images. But what about practical applications which do not use these conventional image datasets? In this article I’ll be walking through a geospatial example of semantic…

We all know that programmers on Wall Street make fortunes with their high-tech code. But let’s actually dive into one and see how it’s really done. Let’s first go over the theory of our algorithm. The backing of this strategy revolves around the assumption that the prices of non-derivative assets…

The lack of diversity within venture capital is something I have been hard at work to try and remedy and I write about frequently. In my last post, I laid out the demographic breakdowns of the venture industry and sought to disprove the notion that the reason that there are…

Observation bias and sub-group differences generate statistical paradoxes. — Observation bias and sub-group differences can easily produce statistical paradoxes in any data science application. Ignoring these elements can therefore completely undermine the conclusions of our analysis. It is indeed not unusual to observe surprising phenomena such as sub-groups trends that are completely reverted in the aggregated data. …

Introduction Gridcoin is not new. It was created in 2013 by Rob Halförd (pseudonym). The protocol rewards people for contributing to scientific research. It’s explained on the website as: Gridcoin is an open source cryptocurrency (Ticker: GRC) that rewards volunteer computing for science. — [1] A post [2] about the project…