Unfolding the universe of possibilities..

Journeying through the galaxy of bits and bytes.

Continuous Learning: A Data Scientist’s Odyssey

Navigating the ever-changing field Continue reading on Towards Data Science »

Cultural Competencies for Machine Learning Risk Management

An organization’s culture is an essential aspect of responsible AI. Continue reading on Towards Data Science »

Machine Learning, Illustrated: Incremental Learning

How models learn new information over time, maintaining and building upon previous knowledge Continue reading on Towards Data Science »

3 Easy Methods For Improving Your Large Language Model

Enhancing the power of Llama 2 Continue reading on Towards Data Science »

LLM Monitoring and Observability

LLM Monitoring and Observability — A Summary of Techniques and Approaches for Responsible AI Intended Audience: Practitioners who want to learn what approaches are available and how to get started implementing them, and leaders seeking to understand the art of the possible

Language Models for Sentence Completion

A practical application of a language model that picks the most likely candidate word that extends an English sentence by a single word Photo by Brett Jordan on Unsplash Co-authored with Naresh Singh. Table of contents IntroductionProblem StatementBrainstorming a solution Algorithms and Data StructuresNLP (Natural

Rubik and Markov

Image from Unsplash modified by the author Here we obtain the probability of optimally solving the Rubik’s cube The Rubik’s cube is a prototype of a planning problem with a colossal state space and only one solution. It is the very definition

From Paper to Pixel: Evaluating the Best Techniques for Digitising Handwritten Texts

A Comparative Dive into OCR, Transformer Models, and Prompt Engineering-based Ensemble Techniques By: Sohrab Sani and Diego Capozzi Organisations have long grappled with the tedious and expensive task of digitising historical handwritten documents. Previously, Optical Character Recognition (OCR) techniques, such as