towardsdatascience.com

Programming Fairness in AlgorithmsUnderstanding and combating issues of fairness in supervised learning.“Being good is easy, what is difficult is being just.” ― Victor Hugo“We need to defend the interests of...

InformationalInstructions on how to approach knowledge acquisition through published research papers by a recognized figure within the world of machine learning and educationPhoto by Annie Spratt on Unsplash“Wisdom...

Example traffic signs from the datasetIntroductionAmazon SageMaker is a cloud machine-learning platform that enables developers to create, train, and deploy machine-learning models in the cloud. I previously used...

Image recognition does not always require neural nets; efficiency and accuracy are achievable with simpler modelsMemes featuring characters from television shows, reproduced here for the purpose of teaching as...

Transformers, one concept at a time1 | Basics of Self-AttentionTL;DR — Transformers are an exciting and (relatively) new part of Machine Learning (ML) but there are a lot of concepts that need to be broken down...

Taking a look at the state of the World through the century with cool data visualisations.Photo by slon_dot_pics from PexelsYou come out from an evening of political discussion and music at the symposium. While going...

Learn to train an SVM model following best practicesPhoto by Kevin Ku on UnsplashFollowing my previous post, I will be covering how we can apply Support Vector Machines using python and Scikit-Learn on a real world...

Different ways to Combine your Deep Learning ModelsPhoto by Noah Rosenfield on UnsplashThe concept of ‘ensembling’ is common in machine learning. Different algorithms are built on this mechanism. Only to cite the...

A DAG that runs a “goodbye” task only after two upstream DAGs have successfully finished. This post explains how to create such a DAG in Apache AirflowIn Apache Airflow we can have very complex DAGs with several...

Monthly EditionNatural Language Processing and the Future of AIPhoto by Elina Krima from PexelsBy now, many of us have interacted with a device’s built-in assistant. Possibly on purpose or even by saying “Are you...

Try to use PCA but stuck at processing stage? Check this out!Siyun Wang (co-author of this article). A fluffy bird on a branch [water color] (2020). We used low-poly art to indicate the feeling of PCA, which is...

How to know if you’ve picked the right modelPhoto by Michelle Tresemer on UnsplashIn machine learning, when faced with a mountain of unlabeled data, a data scientist’s first impulse is to try clustering the data....

Exploring the depths of human consciousnessLet me start by declaring my motivation for writing about a topic I have no explicit authority on. I’ve been writing for years by now, both on topics I work on with my...

Photo by Luke Chesser on UnsplashIntroduction: This article explains the math and execution of univariate linear regression. This will include the math behind cost function, gradient descent, and the convergence of...

Getting Machine Learning/image processing onto the GPU on a small processor running embedded Linux using OpenCL for real-time performance(Image by Wikipedia)Contents:OverviewTravels to find a workable solutionBuild...

Production Perig/Shutterstock.comPart III — FDA Should Not Expand Its Oversight of Commercialized AIIn Part I of this series, I outlined FDA’s existing statutory authority to oversee the commercialization of...

Here’s the complete road-map to learn Data Science from “Zero to Hero” with source links provided.Photo by Campaign Creators on UnsplashTable of contents — Learning path:IntroductionSoft skills required...

Irrespective of architecture, CNNs recognise objects with similar strategies: but humans use a very different one.We know so much and yet so little about convolutional neural networks (CNNs). We have access to every...