How to Build a Data-Driven Customer Management System | by Hans Christian Ekne | Nov, 2024
Image created by the author using Canva Although a basic CBM system will offer some solid benefits and insights, to get the maximum value out of a CBM system, more advanced components are needed. Below we discuss a few of the most important components, such as having churn models with multiple time horizons, adding price […]
LoRA Fine-Tuning On Your Apple Silicon MacBook | by Matthew Gunton | Nov, 2024
Let’s Go Step-By-Step Fine-Tuning On Your MacBook Image by Author — Flux.1 As models become smaller, we are seeing more and more consumer computers capable of running LLMs locally. This both dramatically reduces the barriers for people training their own models and allows for more training techniques to be tried. One consumer computer that can […]
Third-Year Work Anniversary as a Data Scientist: Growth, Reflections and Acceptance | by Zijing Zhu, PhD | Nov, 2024
picture by author A letter to myself and fellow data scientists Dear Zijing, Yesterday, your coworker messaged you that a celebration was held onsite for several work anniversaries, including yours. How time flies! At the end of the month, you will complete three years in this role. Is it true that as we get older, […]
Feature Engineering Techniques for Healthcare Data Analysis | Real-World Examples & Insights by Leo Anello
Feature engineering techniques for healthcare data analysis, focusing on real-world challenges and practical solutions. Photo by Irwan on Unsplash In this tutorial, we continue the project Techniques in Feature Engineering: Real-World Healthcare Data Challenges — Part I, diving into a new series of feature engineering techniques. Project link: GitHub This time, we’ll leverage domain knowledge […]
Dance Between Dense and Sparse Embeddings: Enabling Hybrid Search in LangChain-Milvus | Omri Levy and Ohad Eytan
Image by the author If you swap the queries between the two examples above, and use each one with the other’s embedding, both will produce the wrong result. This demonstrates the fact that each method has its strengths but also its weaknesses. Hybrid search combines the two, aiming to leverage the best from both worlds. […]
Attention (is not) all you need. An alternative approach to the… | by Josh Taylor | Nov, 2024
An alternative approach to the transformer model for text generation Can fractal patterns help us to create a more efficient text generation model? Photo by Giulia May on Unsplash Since the release of ChatGPT at the end of November 2022, LLMs (Large Language Models) have, almost, become a household name. Worldwide search interest for ‘LLM’. […]
Agentic Mesh — Principles for an Autonomous Agent Ecosystem | by Eric Broda | Nov, 2024
Foundational principles that let autonomous agents find each other, collaborate, interact, and transact in a growing Agentic Mesh ecosystem. Source: Eric Broda We are at the earliest stages of agent evolution. But with the massive investments being made in agent technology, I expect that quite soon we will have truly autonomous agents that act independently […]
NER in Czech Documents with XLM-RoBERTa using 🤗 Accelerate | by Bohumir Buso | Nov, 2024
🤗 AccelerateHaving started in a time when wrappers were less common, I became accustomed to writing my own training loops, which I find easier to debug – an approach that 🤗 Accelerate supports effectively. It proved beneficial in this project – I wasn’t entirely certain of the required data and label formats or shapes and […]
Excel Spreadsheets Are Dead for Big Data. Companies Need More Python Instead. | by Ari Joury, PhD | Nov, 2024
Opinion Data is getting too complicated for Excel to keep up Python is taking over what used to be Excel-dominated terrains. Image generated with Leonardo AI Spreadsheets are bogging us down. For all the reliance on Excel in the corporate world, clinging to it is like trying to run a Formula 1 race in a […]
Open the Artificial Brain: Sparse Autoencoders for LLM Inspection | by Salvatore Raieli | Nov, 2024
|LLM|INTERPRETABILITY|SPARSE AUTOENCODERS|XAI| A deep dive into LLM visualization and interpretation using sparse autoencoders Image created by the author using DALL-E All 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 […]