Image for post
Image for post

Are our phones listening to us? It’s a concern that I hear about in casual conversation more and more frequently. I’ve also been seeing a lot more tape on laptop webcams. Why is everyone being so paranoid all of a sudden?

Get out your tin foil hats, because we are all under surveillance. As it turns out, if you are doing anything on a smart device or online, you are probably being watched. Not physically (although maybe), but every imaginable metric about your online activity is being recorded. …


Image for post
Image for post
Local children pump ground water in the Mara River Basin, Tanzania. © Ana Lemos 2016 http://maraselva.fiu.edu/en/fetching-water-on-a-saturday-morning/

Goals and Overview

Tanzania has one of the fastest growing economies in Africa and despite it’s economic success, only approximately 50% of the population have access to clean water. Home to mostly arid environments, many areas of the country are lacking water. The areas that do have water are sourced from basins, many of which are being heavily polluted. This lack of access to clean water forces many people to rely on contaminated supplies, putting many lives at risk.

To combat the water crisis, water pumps have been installed all over the country to provide clean water to the people of Tanzania. The organizations Taarifa and the Tanzanian Ministry of Water have kept detailed data logs on close to 60,000 of the water pumps that have been installed. Through wear and tear, many of these pumps are non-functional or in need of repairing. It is crucial for these organizations to be able to determine when a pump might need replacement or repair so that the people who rely on these waterpoints are safe and have access to clean water. It is for this reason that Taarifa has hosted an online competition with the goal of creating predictive models to determine the functionality status of the water pumps in the country. …


Image for post
Image for post
Face generated by a GAN

Goals and Overview

A Generative Adversarial Network (GAN) is a type of neural network for generative modeling. The generative model is trained using two neural network models: a generator and a discriminator. GANs are complex so to put them in laymen’s terms, the way they work is there is a generator model that learns to generate plausible samples from a dataset. …

About

John Kundycki

Data Scientist | Health Enthusiast | Learner

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store