Unfolding the universe of possibilities..

Dancing with the stars of binary realms.

5 Steps to Build Beautiful Line Charts with Python

How to use the full capabilities of Matplotlib to tell a more compelling story Continue reading on Towards Data Science »

Super Charge Your ML Systems In 4 Simple Steps

Image generated with DALL.E-3 Welcome to the rollercoaster of ML optimization! This post will take you through my process for optimizing any ML system for lightning-fast training and inference in 4 simple steps. Imagine this: You finally get put on a cool

Python Callables: The Basics and the Secrets

Learn how powerful Python callables can be. Continue reading on Towards Data Science »

Don’t Apply to Tech Without Mastering These 6 Must-Have Data Science Skills — A Spotify Data…

A glimpse into the wizarding world of Tech & what you need to make your way in and succeed as a Data Wizard-ist Continue reading on Towards Data Science »

Quantisation and co. Reducing inference times on LLMs by 80%

Showing techniques to optimise your own LLMs — with code examples Continue reading on Towards Data Science »

Decision Science Meets Design

A Dive into Solving Generative Design Problems Through Deep Reinforcement Learning Continue reading on Towards Data Science »

Well Log Measurement Prediction Using Neural Networks with Keras

An example of predicting bulk density (RHOB) with Keras and illustrating impacts of normalisation on prediction results Continue reading on Towards Data Science »

Outlier Detection with Scikit-Learn and Matplotlib: a Practical Guide

Learn how visualizations, algorithms, and statistics help you to identify anomalies for your machine learning tasks. Continue reading on Towards Data Science »

Managing Multiple CUDA Versions on a Single Machine: A Comprehensive Guide

How to Handle Different CUDA Versions in Your Development Environment Photo by Nikola Majksner on Unsplash In one of my previous roles as an AI consultant, I was tasked with utilizing virtual environments as a tool for managing and isolating Python

Why Probabilistic Linkage is More Accurate than Fuzzy Matching or Term Frequency based approaches

How effectively do different approaches to record linkage use information in the records to make predictions? Wringing information out of data. Image created by the author using DALL·E 3 A pervasive data quality problem is to have multiple different records that