Month: May 2023

Using spatial data science to model populations + analysing educational equity in Tirana. Published in · 5 min read · 1 hour ago Photo by Gledisa Golikja on Unsplash Hello! … Read more

Challenges in Dask Distributed Implementation In order to utilise CuSpatial’s spatial join function “point_in_polygon”, the latitude and longitude points must be stored in an interleaved array format: #interleaved[lon,lat,lon,lat,lon,lat,lon,…]#instead of[[lon,lat],[lon,lat],[lon,lat],[lon,lat],[lon,lat],…] This … Read more

In October 2022, I published an article on LLM selection for specific NLP use cases , such as conversation, translation and summarisation. Since then, AI has made a huge step … Read more

Published in · 7 min read · 5 hours ago Image by Google DeepMind on Unsplash Artificial intelligence (AI) has come a long way since its inception in the 1950s. … Read more

Specific points from multiple reviews We are doing an analysis on device setup and want to learn if users have issues setting up the device. We can extract parts related … Read more

A whirlwind tour of Machine Learning Lifecycle Management Published in · 6 min read · 8 hours ago Photo by Stephen Dawson on Unsplash Have you ever found yourself training … Read more

Problem 3 — Fence-throwing Dehghani calls the third and final mode of failure siloed and hyper-specialised ownership, which I like to think as resulting in unproductive fence-throwing. Our hyper-specialised big … Read more

Improve workflows and expectation management in ML through technical drawings Published in · 8 min read · 1 hour ago Machine Learning (ML) projects are becoming increasingly popular in business … Read more

Learn how to use GPT-3.5 to do the heavy lifting for data acquisition, preprocessing, model training, and deployment Published in · 14 min read · 4 days ago A lot … Read more

THE DUAL-EDGED SWORD OF LARGE LANGUAGE MODELS (LLMs) You thought the 2016 Brexit and US presidential campaigns were bad? Think again. Published in · 16 min read · Just now … Read more

Here I will first summarize the explosion of research studies during the past year on a high level, and then follow up with a summary of the various technical details. … Read more

What is an Embedding? Embedding (also called Vector Embeddings) is a series of vectors providing a mathematical representation of words or sentences. The vectors capture the semantic meaning and context … Read more

To showcase the power of PyTorch Explain, let’s dive into our first tutorial! A primer on concept bottleneck models In this introductory session, we’ll dive into concept bottleneck models. These … Read more

In the rest of this article, we’ll forecast dew point temperature in several locations. You’ll learn how to build a spatio-temporal forecasting model using deep learning. The full code for … Read more

Calculating cloud cover in your area of interest, removing clouds and inpainting them using another satellite image Published in · 14 min read · 7 hours ago (source: author) Our … Read more

Prompt Engineering, SVG A quick tutorial on how to write proper prompts to make ChatGPT generate diagrams Published in · 4 min read · 11 hours ago Photo by Christina … Read more

A Ph.D. student’s exploration of the surprising parallels between academic and industrial data science Published in · 8 min read · Just now Photo by Campaign Creators on Unsplash As … Read more

More sophisticated approaches to solving even more complex tasks are now being actively developed. While they significantly outperform in some scenarios, their practical usage remains somewhat limited. I will mention … Read more

Clean, process and tokenise texts in milliseconds using in-built Polars string expressions Published in · 10 min read · Just now Photo by Stephen Phillips – Hostreviews.co.uk on Unsplash With … Read more

Published in · 6 min read · 1 hour ago Photo by James Stamler on Unsplash In this post, we explore Google’s innovative approach to training their remarkable text-to-music models, … Read more

Published in · 10 min read · 2 hours ago Source: DreamStudio (generated by author) Ask GPT-4 to prove there are infinite prime numbers — while rhyming — and it … Read more

Clustering of Twitter data with Python, K-Means, and t-SNE Published in · 17 min read · Just now Tweet clusters t-SNE visualization, Image by author In the article “What People … Read more

Explore the cutting-edge multilingual features of Meta’s latest automatic speech recognition (ASR) model Published in · 8 min read · 1 hour ago Massively Multilingual Speech (MMS)¹ is the latest … Read more

Single-threaded recursive algorithms There are algorithms that per design are not a subject of parallelization — recursive algorithms. In recursion, the current value depends on the previous values — one … Read more

Different Statistical Approaches to Detecting AI-generated Text. Published in · 6 min read · Just now Photo by Andreas Fickl on Unsplash In the fascinating and rapidly advancing realm of … Read more

The answer lies in the 75 years of NLP history Published in · 6 min read · 1 hour ago Photo by Romain Vignes on Unsplash Have you ever wondered … Read more

By virtue of writing code in the Hamiltonian way, you are defining computation within functions, and then specifying via function input arguments, how things connect, encoding lineage. Taking this code … Read more

Learn the underlying working of various unsupervised machine learning models and how they are able to generate predictions without output labels Published in · 12 min read · 1 day … Read more

The code we’ll be working with in this piece is this set of Python functions that use Pandas to read in and process data. It includes a function to read … Read more

Stop waiting and start multi-threading Published in · 4 min read · 2 hours ago Photo by Max Wolfs on Unsplash Even though Julia is one of the fastest languages … Read more