Juha Jokela

Do you know how time series data is stored in memory? 🤔 This blog explains the compression algorithms that power massive-scale time series data stores. We take a case-study of Meta's GorillaDB here: Time Series Compression Algorithm Blog. Read Now: https://lnkd.in/dBG_GQtZ Get 70% off on all our courses by using DESIGN70 code. Cheers!

7

New Post: More Agents Is All You need This paper introduces a method that significantly enhances Large Language Model (LLM) performance by scaling up the number of agents using a sampling- https://buff.ly/44Lmmvi

1

Exploring the future of AI with Retrieval-Augmented Generation (RAG). This technique enhances user query responses by leveraging large language models and vector databases. Learn more from Eivind Kjosbakken. #MachineLearning #RAG

10

A Survey of RAG and RAU: Advancing Natural Language Processing with Retrieval-Augmented Language Models Quick read: https://lnkd.in/gnGqk44W Paper: https://lnkd.in/g8-VftbX #llms #largelanguagemodels #ai

20

How network & web knowledge makes us better ML Engineers 🧠➡️🌐 As Machine Learning engineers, we’re often deep in the weeds of algorithms and models, but to build end-to-end systems, we need a broader perspective. Last week, at Modulai’s Learning Breakfast, our Machine Learning Engineer Svante Sörberg explored how we benefit from understanding computer networks and web fundamentals: 1️⃣ Better Systems Thinking & Design Understanding how data moves from Point A to B enables us to design more efficient ML pipelines and system architectures. It’s like knowing the highways that connect cities—you can’t optimize traffic flow without understanding the roads. 2️⃣ Informed Decision-Making Knowing the web stack helps us make better trade-offs in our ML systems. For instance, leveraging HTTP cache mechanics in our APIs can significantly reduce latency and cost, making our solutions more efficient and responsive. 3️⃣ Security by Design A solid grasp of network protocols and web security principles empowers us to build secure ML solutions from the ground up. This includes protecting against attacks and ensuring privacy-preserving data collection and transmission—a critical consideration in today’s data-driven world. 4️⃣ Web Scraping & Data Collection Many ML projects require web scraping or API integration for data collection. Familiarity with HTTP methods, status codes, and headers ensures we’re getting accurate, relevant data from the start. 5️⃣ Full-Stack ML Engineering As the line between ‘ML’ and ‘software engineering’ blurs, knowing web fundamentals equips us to independently build end-to-end ML products—a powerful skill as ML becomes increasingly embedded in all layers of technology. Building impactful solutions requires both depth and breadth, and every new skill helps us take that next step. Let’s keep expanding, learning, and redefining what’s possible in ML. What skills have helped you build stronger ML systems? Drop your insights below! 👇 #MachineLearning #Modulai #LearningBreakfast #SystemsThinking #WebFundamentals #FullStackML #EngineeringExcellence #InterdisciplinarySkills

17

Are you ready for a deep dive session into the word of Generative AI? Jeppe Christensen wrote this explanatory blog post where he describes: 🌟The history of Generative AI 🌟The ChatGPT phenomenon 🌟The difference with traditional Artificial Intelligence 🌟Benefits, uses, and challenges It's a must-read! Take a look: https://bit.ly/3Xrjkdj #GenAI #Llms #ChatGPT

33

1 kommentti

Discover the Power of AI: Comparing Llama-3 and Phi-3 Using RAG 🚀 We are excited to share a fantastic resource recently released on Lightning AI's platform! This tutorial, titled "Compare Llama-3 and Phi-3 using RAG", offers an insightful and practical approach to understanding the capabilities and differences between two cutting-edge AI models, Llama-3 and Phi-3, through the Retriever-Augmented Generation (RAG) framework. 👉 What's Inside? The tutorial is a hands-on guide that walks you through the steps of setting up and running comparisons between Llama-3 and Phi-3. It provides a detailed overview of how each model performs in various tasks and how their results can be enhanced using the RAG technique. Whether you're a researcher, a data scientist, or simply an AI enthusiast, this tutorial is designed to enrich your understanding of modern AI technologies. 🔍 Why It Matters? Understanding the nuances between different AI models helps in choosing the right tool for specific applications, enhancing both efficiency and effectiveness in projects. The tutorial not only sheds light on the models' capabilities but also demonstrates the practical applications of these technologies in real-world scenarios. 🌐 Check out the full tutorial here: https://lnkd.in/ewZu3G_M

8

This repository by Nir Diamant offers a wide range of strategies for RAG (currently 17), along with tutorials and visualizations, making it an excellent resource for learning and reference. https://lnkd.in/gia_ktaF #python #Programming #PythonProgramming #DataScience #MachineLearning #SoftwareDevelopment #WebDevelopment #TechNews #OpenSource #DataEngineering

3

2 kommenttia

Building a Simple text Classifier with Semantic Kernel In this blog post, we’ll explore how to use Semantic Kernel to build a simple Natural Language Processing (NLP) classifier. https://lnkd.in/dkdQeK-5

10

Interested in "prompt engineering?" Consider letting the models generate prompts for you. Check out our automated prompt engineering tool for making more beautiful images with GPT-4 and DALL-E-3 from your command line. The tool is only ~200 lines of Python. This is the sort of thing you'd be able to write after taking one of our Intro to Python classes!

3

Today, we will walk through how to evaluate these #LLMs for better performance through a simple tutorial. https://lnkd.in/eUgS3Hf9

1

🎉 Now available in Timbr! Leverage ChatGPT to transform any ERD image into an SQL semantic data model in just a few simple clicks! ⚡ 🔗 https://lnkd.in/dB6HT4Gn #SemanticModeling #DataModeling #data #dataarchitecture #azure #DataWarehouse #AgileData #DataCloud #DataAnalytics #DataIntegration #DataManagement #DataLake #DataHub #dataarchitecture #DataManagement #Lakehouse #DataMesh #BigData #dataengineering #knowledgegraphs #semanticlayer #spark #sql

9

Our larger goal at Kùzu Inc. is to make graph databases and knowledge graphs accessible to a much larger community, through our focus on ease-of-use, scalability and performance. Toward this end, Semih Salihoğlu is preparing a series of videos introducing the core concepts of #graph databases and their feature set. ✅ If you are new to graph databases, this series is a great way to become familiar with the key concepts to get started with graphs. ✅ If you're familiar with graph data models, this series is a great way to understand the principles behind Kùzu and to begin using it in your projects. The first video in the series is now out! Give it a watch, and share around 🤝🏽. Subscribe to our YouTube channel for more such videos to be released in the coming weeks! https://lnkd.in/gqdGTqYf Video: https://lnkd.in/gsejgP8w Kùzu GitHub: https://lnkd.in/dUXZH6sT

14

🎉 aGrUM/pyAgrum 1.16.0 is now available! 🎉 The latest version of aGrUM/pyAgrum is packed with new features and updates: 🔹 Enhanced Structure Learning: Now you can use NoParentNode and NoChildNode constraints to fine-tune 👩‍🔬 Bayesian network learning. 🔹 New in Causal Inference: We’ve added (conditional) Average Causal Effect/Average Treatment Effect (ACE/ATE) estimation with meta learners. Curious 🧐 to see it in action? Check out our example notebooks: Causal Effect Estimation (https://lnkd.in/eA44aHW4) Examples of Causal Effect Estimation from Data (https://lnkd.in/ezmkPwif) 👋😢 Farewell, Python 3.9: With this release, we also say goodbye to Python 3.9 support. 💻 Download the latest version to explore all the new features! For the complete list of changes, visit the changelog here: https://lnkd.in/etNV7wR4 #pyAgrum #Python #BayesianNetworks #AI #DataScience

23

GenAI iteration speed is growing exponentially. One outcome is that the context window — the number of tokens a large language model (LLM) can use at one time to generate a response — is also expanding rapidly. https://lnkd.in/dr5njXhM #Database #AI #LargeLanguageModels by Usama Jamil thanks to MyScale

2