Unfolding the universe of possibilities..

Dancing with the stars of binary realms.

Handling Gaps in Time Series

Missingness analysis and evaluation methods for short and long sequences imputation Continue reading on Towards Data Science »

Fine Tuning LLMs on a Single Consumer Graphic Card

Learnings from fine tuning a large language model on a single consumer GPU Continue reading on Towards Data Science »

Revolutionizing Culinary Experiences with AI: Introducing FIRE (Food Image to REcipe generation)

From Visual Delights to Culinary Recipes: How AI Transforms Food Images into Recipes? Figure 1. Given a potentially unseen image, our method FIRE generates a corresponding recipe consisting of a title, ingredients, and cooking instructions. (Source: Image by the author) Introduction: Food

What Is the Biggest Number?

In the abstract world that we call home, how many digits do we need? A non-technical journey to the longest sum of all Continue reading on Towards Data Science »

Basics of Reinforcement Learning for LLMs

Understanding the problem formulation and basic algorithms for RL Continue reading on Towards Data Science »

Understanding Junctions (Chains, Forks and Colliders) and the Role they Play in Causal Inference

Explaining junctions using correlation, independence and regression to understand their critical importance in causal inference Continue reading on Towards Data Science »

Lingua Franca — Entity-Aware Machine Translation Approach for Question Answering over Knowledge…

Lingua Franca — Entity-Aware Machine Translation Approach for Question Answering over Knowledge Graphs Towards a lingua franca for knowledge graph question answering systems TLDR Machine Translation (MT) can enhance existing Question Answering (QA) systems, which have limited language capabilities, by enabling them

Don’t Fix Bad Data, Do This Instead

People don’t know what they mean when they talk about Data Quality. Continue reading on Towards Data Science »

Run LLM inference using Apple Hardware

Unlock Apple GPU Power for LLM Inference with MLX Continue reading on Towards Data Science »

How to Use Zero-Shot Classification for Sentiment Analysis

Exploring mental well-being insights with zero-shot classification Artwork by Vivian Peng — reposted with permission Sentiment analysis is a powerful tool in natural language processing (NLP) for exploring public opinions and emotions in text. In the context of mental health, it can