Stories by TDS Team on Medium

Stories by TDS Team on Medium

Latest articles

Explain Yourself! Leveraging Language Models for Common Sense Reasoning

EVENT TALKSNazneen Rajani | TMLS2019https://medium.com/media/3fd6f64e8029bfbf8289a9e3d7610a3d/hrefAbout the speakerNazneen Fatema Rajani is a senior research scientist at Salesforce Research. LinkedinAbout the talkDeep learning models perform poorly on tasks that require commonsense reasoning, which often necessitates some form of world-knowledge or...

Big data: yesterday, today, and tomorrow

U.S. Army Photo, n.d. Public DomainWhat is “Big Data” — Understanding the HistoryBy James Winegar — 18 min readA tour through history, how we ended up here, what capabilities we’ve unlocked, and where we go next?Photo by Guillermo Ferla on UnsplashA Fresh Look at Clustering AlgorithmsBy Dmitry Selemir — 14 min readThe project is by no means in its final...

Evaluating Bayesian Mixed Models

Photo by Andrew DesLauriers on UnsplashEvaluating Bayesian Mixed Models in R/PythonBy Eduardo Coronado Sroka — 17 min readIn this article, my goal guide is you through some useful model checking and evaluation VISUAL METHODS for Bayesian models (not your typical RMSE) in both R and Python.UnsplashThe Multi-Channel Neural NetworkBy Eugenio Zuccarelli — 7...

From Idea to Production

How to take a data science project from idea to productionBy Kate Marie Lewis — 16 min readI have interviewed a lot of data science candidates for various roles. From junior data scientists to hiring the head of the data science team I was working in. Throughout the myriad of interviews where I have been on the hiring panel, there are a few questions...

Beyond Weisfeiler-Lehman: using substructures for provably expressive graph neural networks

By Michael Bronstein — 8 min readIn this post, I discuss how to design local and computationally efficient provably powerful graph neural networks that are not based on the Weisfeiler-Lehman tests hierarchy. This is the second in the series of posts on the expressivity of graph neural networks. See Part 1 describing the relation between graph neural...

DevOps for ML and other Half-Truths: Processes and Tools for the ML Life Cycle

EVENT TALKSKenny Daniel | TMLS2019https://medium.com/media/4c93c8226cfcf7acf1eecb9feb29b918/hrefAbout the speakerKenny Daniel is a founder and CTO of Algorithmia. He came up with the idea for Algorithmia while working on his PhD and seeing the plethora of algorithms that never saw the light of day.In response, he built the Algorithmia Cloud AI Layer,...

Data Analysis in python: Getting started with pandas

By Kerry Parker — 13 min readPandas is a python tool used extensively for data analysis and manipulation. Recently I’ve been using pandas with large DataFrames (>50M rows) and through the PyDataUK May Talks and exploring StackOverflow threads have discovered several tips that have been incredibly useful in optimising my analysis.Pneumonia Detection:...

July Edition: Hey Siri, What Do I Mean?

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 serious?” too close to an iPhone. Whether it’s Alexa, Siri, or whomever lives inside your preferred smart device; it’s using natural language...

Measuring Statistical Dispersion with the Gini Coefficient

By Kimberly Fessel — 11 min readThis post includes a thorough mathematical explanation of the Gini coefficient as well as a few non-standard applications to baby names and healthcare pricing.A Bayesian Approach to Linear Mixed Models (LMM) in R/PythonBy Eduardo Coronado Sroka — 12 min readThere seems to be a general misconception that Bayesian methods...

Expressive power of graph neural networks and the Weisfeiler-Lehman test

By Michael Bronstein — 8 min readDo you have a feeling that deep learning on graphs is a bunch of heuristics that work sometimes and nobody has a clue why? In this post, I discuss the graph isomorphism problem, the Weisfeiler-Lehman heuristic for graph isomorphism testing, and how it can be used to analyse the expressive power of graph neural networks.The...

Discover, share and read the best on the web

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
Inoreader - Subscribe to RSS Feeds, Blogs, Podcasts, Twitter searches, Facebook pages, even Email Newsletters!