How fast will you drive? Photo by Julian Hochgesang on UnsplashWhen planning future vehicle routes, you trust the digital map providers for accurate speed predictions. You do this when picking your phone up to prepare for a car trip or, in a professional setting, when planning routes for your vehicle fleet. The forecasted speeds are…

Explore building an advanced RAG system on your computer. Full-cycle step-by-step guide with code. Image by the Author | Mistral + LlamaIndex + W&BRetrieval Augmented Generation (RAG) is a powerful NLP technique that combines large language models with selective access to knowledge. It allows us to reduce LLM hallucinations by providing the relevant pieces of…

IntelliCar is a European-based company that recently started producing smart cars for the European market. In order to get the desired answer when looking into the magic mirror and asking who has the smartest car of them all, IntelliCar thought long and hard and decided to equip their super smart cars with: facial and emotion…

Utilize SageMaker Pipelines, JumpStart, and Clarify to Fine-Tune and Evaluate a Llama 7B Model Image from Unsplash by Sigmund2023 was the year that witnessed the rise of various Large Language Models (LLMs) in the Generative AI space. LLMs have incredible power and potential, but productionizing them has been a consistent challenge for users. An especially…

Environment setup In this guide, we’re going to use JupyterLab with Docker and MinIO. Think of Docker as a handy tool that simplifies running applications, and MinIO as a flexible storage solution perfect for handling lots of different types of data. Here’s how we’ll set things up: I’m not diving deep into every step here…

Photo by Element5 Digital on UnsplashA Bonus Article for “The Book of Why” Series In two months, we finished reading “The Book of Why,” which gave us a glimpse into the fascinating world of causality. As promised, I have a bonus article to close my first Read with Me series officially. Inspired by my own…

When ReLU’s extrapolation capabilities are not enough Photo by Willian Justen de Vasconcellos on UnsplashNeural networks are known to be great approximators for any function — at least whenever we don’t move too far away from our dataset. Let us see what that means. Here is some data: Image by the author.It does not only…

A 5-Step Guide to Leveling Up In 2024 Photo by Vidar Nordli-Mathisen on UnsplashIn the rapidly expanding technological world of today, getting a job in the data industry is the first step to what could be a larger data career. Now that you are a Data Analyst, what happens next? As a common way of…

Luca Naef (VantAI) 🔥What are the biggest advancements in the field you noticed in 2023? 1️⃣ Increasing multi-modality & modularity — as shown by the emergence of initial co-folding methods for both proteins & small molecules, diffusion and non-diffusion-based, to extend on AF2 success: DiffusionProteinLigand in the last days of 2022 and RFDiffusion, AlphaFold2 and…

And so, it appears that the answer is not a fight to the death between CNNs and Transformers (see the many overindulgent eulogies for LSTMs), but rather something a bit more romantic. Not only does the adoption of 2D convolutions in hierarchical transformers like CvT and PVTv2 conveniently create multiscale features, reduce the complexity of…