|LLM|INTERPRETABILITY|SPARSE AUTOENCODERS|XAI| A deep dive into LLM visualization and interpretation using sparse autoencoders Image created by the author using DALL-EAll things are subject to interpretation whichever interpretation prevails at a given time is a function of power and not truth. — Friedrich Nietzsche As AI systems grow in scale, it is increasingly difficult and pressing…

Learning to transform categorical data into a format that a machine learning model can understand When studying machine learning, it is essential to understand the inner workings of the most basic algorithms. Doing so helps in understanding how algorithms operate in popular libraries and frameworks, how to debug them, choose better hyperparameters more easily, and…

Building a 28% more accurate multimodal image search engine with VLMs. Until recently, AI models were narrow in scope and limited to understanding either language or specific images, but rarely both. In this respect, general language models like GPTs were a HUGE leap since we went from specialized models to general yet much more powerful…

What working as a data scientist at various companies and industries over the past 6+ years has taught me of the future of data science and AI engineering GenAI and Large Language Models (LLMs) continue changing how we work and what work will mean in the future, especially for the data science domain, where in…

And how much I made my first year Photo by Amy Hirschi on UnsplashCongratulations, you have landed a data science position! You open your offer letter and … Well, you’re a bit disappointed. This is completely normal, at least for most companies, and especially if you are a junior or just starting out in the…

How to build ML products users love. 23 min read · Oct 14, 2024 Photo by Pavel Danilyuk: https://www.pexels.com/photo/a-robot-holding-a-flower-8438979/Data science offers rich opportunities to explore new concepts and demonstrate their viability, all towards building the ‘intelligence’ behind features and products. However, most machine learning (ML) projects fail! And this isn’t just…

Working with ODEs Physical systems can typically be modeled through differential equations, or equations including derivatives. Forces, hence Newton’s Laws, can be expressed as derivatives, as can Maxwell’s Equations, so differential equations can describe most physics problems. A differential equation describes how a system changes based on the system’s current state, in effect defining state…

A mini multi-agent competition among 3 different LLM agents Generated using ChatGPT 4o.This article was originally posted on Art Fish Intelligence. LLMs are good at many things, and one of those things is playing games. People have used LLMs to play all sorts of games such as Minecraft, Chess, murder mystery games, Werewolf, and the…

As illustrated in figure 1, DSPy is a pytorch-like/lego-like framework for building LLM-based apps. Out of the box, it comes with: Signatures: These are specifications to define input and output behaviour of a DSPy program. These can be defined using short-hand notation (like “question -> answer” where the framework automatically understands question is the input…

End-to-end Project Implementation 19 min read · Aug 29, 2024 Image created by the authorDeveloping, deploying, and maintaining machine learning models in production can be challenging and complex. This is where Machine Learning Operations (MLOps) comes into play. MLOps is a set of practices that automate and simplify machine learning (ML)…