It’s Open Source, plays nicely with Kubernetes, and there’s a great communitySource: AuthorBackstory: Why we dropped KubeFlowYou can read more about why we were less than impressed with Kubeflow in our previous post. In short, we’re building a reference architecture for machine learning projects. When it’s done, it’lll be a collection of our favorite...
Tips to Make your Python Modules User FriendlyContinue reading on Towards Data Science »
A sentiment-driven method of identifying which kind of plotline maximizes revenue.Continue reading on Towards Data Science »
Managing Annotation Mistakes with FiftyOne and LabelboxFind annotation mistakes in your image datasets with FiftyOne and fix them in LabelboxPhoto by Johnny McClung on UnsplashAs computer vision datasets are growing to contain millions of images, annotation errors undoubtedly creep in. While annotation errors in training data can be harmful to the performance...
Here are 3 qualities you need to know…Continue reading on Towards Data Science »
Photo by John Moeses Bauan on UnsplashA fast guide on how to use neural networks to solve ODEs (TensorFlow implementation included)The idea of solving an ODE using a Neural Network was first described by Lagaris et al. The insight behind it is basically training a neural network to satisfy the conditions required by a differential equation. In other...
COVID-19 Vaccination Progress Analysis through Data StorytellingDetailed Data Analysis and result-oriented storytelling of COVID-19 vaccination program of different countries across the globe.Designed by: Nevil SutariaThe Covid-19 pandemic is the most important health disaster that has surrounded the world for the past year. Predicting the COVID-19...
How can we use BigQuery to handle tables with many columns? Here’s how using scripting and table metadata.Continue reading on Towards Data Science »
How to Sequence a Human GenomeBy reading the Three Little Pigs and walking through a cityThe human genome contains over three billion base pairs. Just to put that into context, if you examined one base pair each second, it would take over 94 years for you to examine them the entire thing. So it should come as no surprise that somewhat masochistically...
Backtesting frequencies of dollar-cost averaging in stock marketContinue reading on Towards Data Science »
Subscribe to RSS Feeds, Blogs, Podcasts, Twitter searches, Facebook pages, even Email Newsletters! Get unfiltered news feeds or filter them to your liking.Get Inoreader