A few things to consider before clustering your data

Data exploration through medical imaging domain knowledge

Classifying images of oil palm plantations using fast.ai

Descriptive statistics, Exploratory Data Analysis, and Natural Language Processing (NLP) techniques to understand your data.

FiveThirtyEight’s men’s and women’s NCAA Tournament forecasting models calculate the chance of each team reaching each round.

Everything you need to know about a top algorithm in Machine Learning

Neural nets are a type of algorithm — a process that takes in information, processes it somehow, and produces output. In my opinion, they…

After Dan Becker’s “Why Data Science Skill-Building Might Be Holding You Back (And What You Should Be Doing Instead).”…

A first step into the literature

Don't take my DataCamp courses

‘In the egoic state, your sense of self, your identity, is derived from your thinking mind — in other words, what your mind tells you…

Brand Intelligence in the Era of Big Data.

About two months ago, a single tweet almost derailed my productive work day. It caught my attention not just because it included a GIF showing the animated output of a new text-writing AI, but also…

Generating Tang Dynasty poetry using OpenAI GPT2

In this article I would like to explain the concept of probability plots — what they are, how to implement them in Python and how to…

How data size impacts Deep Learning models and how to work with small datasets?

In order to have effective media, it is essential for a media plan to utilize multiple distribution channels (ie digital display, TV, OOH)…

Training and building a custom image classifier mobile app

What is Vega and how you can use it to build visualizations for the web

The latest AI algorithms are probing the evolution of galaxies, calculating quantum wave functions, discovering new chemical compounds and more. Is there anything that scientists do that can’t be automated?

Yeah this is true, be careful editors!! Thanks Python.

A Darth Vader Guide to building Chatbots

To make the model more accurate — simply one-hot encode all categorical features and impute all missing values with zero may not be enough.