Learn how to add your own proprietary data to a pre-trained LLM using a prompt-based technique called Retrieval-Augmented Generation.- 20769Murphy2025-03-23
A Journey of Learning, Improvement, and the Quest for the Ultimate Hybrid Search System- 28268Murphy2025-03-23
Row echelon form and reduced row echelon form- 21625Murphy2025-03-23
What separates junior machine learning practitioners from senior solution architects in a fast-moving industry?- 22350Murphy2025-03-23
Model Mother Nature with Logarithmic Spirals- 28986Murphy2025-03-23
Demonstration of KDE using real-world datasets- 25575Murphy2025-03-23
How to implement effective unit-testing in Python to ensure production-level, bug-free code.- 28115Murphy2025-03-23
Yes, it's much more than data visualization- 22518Murphy2025-03-23
Plain old feed-forward layers and their role in Transformers- 24665Murphy2025-03-23
The Earth is more or less a sphere, certainly a 3D object (despite some challenges even this), while our printed maps and digital screens are 2D. The intermediate step that transforms the sphere into our 2D maps, whether it be a cartographic atlas or a fa- 21912Murphy2025-03-23
Businesses are jumping on a bandwagon of creating something, anything that they can launch as a "Generative AI" feature or product.- 21373Murphy2025-03-23
If you have ever used a language model through a playground or an API, you may have been asked to choose some token sampling parameters. For many of us, the meaning of these parameters (and the right way to use them) is less than totally clear. This artic- 20307Murphy2025-03-23
More efficient language models- 26933Murphy2025-03-23
What is sampling bias in recommendation, and how to correct them- 22856Murphy2025-03-23
In this piece, I combine earlier work on urban accessibility or walkability with open-source data on the location of public defibrillator devices. Additionally, I incorporate global population data and Uber’s H3 grid system to estimate the share of- 30042Murphy2025-03-23
An alternative of logistic regression in special conditions- 26931Murphy2025-03-23
A 3-D simulation of a spiral galaxy (by author) In a previous article, I demonstrated how you could use Python’s Tkinter GUI module to make 2-D galactic art using the equation for a logarithmic spiral [1]. In this article, we’ll take things a- 28902Murphy2025-03-23
Published in Nightingale, Journal of the Data Visualization Society, September 12, 2023. Edited by Kathryn Hurchla. The Manhattan Project was one of the largest scientific collaborations ever undertaken. It operated thanks to a complex social network of e- 20205Murphy2025-03-23
I recently came across this article: HINT: Hierarchical interaction network for clinical-trial-outcome predictions from Fu et al. It’s an interesting application of real-world data science, and it inspired me to create my own project in which I atte- 29804Murphy2025-03-23
In the first part of this series I focused on embedding multi-modal real-world data derived from ClinicalTrials.gov. In this article I will implement a basic XGBoost model, train it on the embeddings we created in Part 1 and compare its performance to tha- 23730Murphy2025-03-23
Why is ChatGPT only trained up until 2021?
Learn how to rearrange your code to achieve significant speed improvements.
