Roman Wixinger

The Rails 8 feature set perfectly complements SQLite's power in creating resilient, high-performance production apps, but still the question lingers: Can I really go all-in on #SQLite? Join Stephen Margheim at #RailsWorld as he illustrates how to leverage Rails and SQLite's full potential in your next venture, and when SQLite does and doesn't make sense for your application. https://lnkd.in/eaBstScy

52

1 Kommentar

🚀 Exciting News! 🚀 We are thrilled to announce that Kumo AI's position paper "Relational Deep Learning: Graph Representation Learning on Relational Databases," has been accepted at #ICML 2024! 🎉 Join us in Vienna from July 21-27, where our very own Matthias Fey will be presenting this exciting new research area. 🔗 https://icml.cc/ In collaboration with Stanford University, we introduce Relational Deep Learning (#RDL), a new research area for applying deep learning on relational databases by viewing them as temporal, heterogeneous graphs. This method eliminates the need for manual feature engineering, leading to more accurate models built faster. 🚀 We’ve also developed #RelBench, a benchmark suite to facilitate research in this new area, using diverse datasets from Stack Exchange discussions to Amazon book reviews. 📚 Stay tuned for more updates on our presentation format, and check out our paper here: https://lnkd.in/dk24vbSg #ICML2024 #MachineLearning #AI #GraphNeuralNetworks #RelationalDeepLearning #DataScience #KumoAI #StanfordCollaboration

38

🚀 𝗢𝘂𝘁 𝗻𝗼𝘄: 𝗧𝘄𝗼 𝗵𝗲𝗶𝘀𝗲 𝗮𝗿𝘁𝗶𝗰𝗹𝗲𝘀 𝗼𝗻 𝗟𝗟𝗠 Alexander Schatten, senior researcher at SBA Research, and Marco Jeppe Reiser have published an interesting article: 📰 𝗪𝗵𝗮𝘁 𝗽𝗿𝗼𝗴𝗿𝗮𝗺𝗺𝗶𝗻𝗴 𝗮𝘁 𝗽𝗿𝗼𝗺𝗽𝘁 𝗹𝗲𝘃𝗲𝗹 𝗹𝗲𝗮𝗱𝘀 𝘁𝗼 Where can AI systems really help programmers, and is the approach taken here truly novel? This article examines their role. Programming involves interpreting real-world problems and processes, abstracting them, and then translating them into a deterministic language understood by technical systems. The goal is to automate tasks and processes and interact with people or other systems as needed. Besides understanding the real-world problem, programming also requires technical consideration of advantages and disadvantages, costs, legal frameworks, dependencies, and more. Actual coding is only a small part of the whole process. Alexander Schatten's second article on heise online explores the role of LLMs in software development. 📰 𝗟𝗟𝗠𝘀 𝗶𝗻 𝘀𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁: 𝘄𝗵𝗮𝘁 𝘁𝗵𝗲𝘆 𝗯𝗿𝗶𝗻𝗴 𝗮𝗻𝗱 𝘄𝗵𝗲𝗿𝗲 𝘁𝗵𝗲𝘆 𝗵𝗮𝘃𝗲 𝗳𝗮𝗶𝗹𝗲𝗱 Software systems are a combination of hardware, software, and the people who develop, maintain, and use these systems. This interaction of the three factors creates benefits and the possibility of further system development. Early on, software exhibited characteristics not observed in other technical systems. The first software crisis in the 1960s revealed that hardware and software capabilities were growing faster than those of human engineers, a crisis from which we have not yet fully emerged. One reason is the ever-increasing complexity of software itself and the complexity created by software and its increasing networking with other systems, affecting software further. Get the full articles here:   https://lnkd.in/gA2hHCBb   https://lnkd.in/giAV6f8C    Both articles will soon be published in iX magazine. 📷: Marcel Lehner 

19

A great read on the performance and financials of LLM fine-tuning. Really hoping the outcome is a tool that helps overcome the biggest elephant in the room, Mr. Cost! #llm #finetuning #finance #computaioncosts

2

1 Kommentar

In Daniel Klitzke's latest article, he shows how you can use the Huggingface Transformers and Sentence Transformers libraries to boost you RAG pipelines using reranking models. #LLM #MachineLearning

22

AnchorGT: A Novel Attention Architecture for Graph Transformers as a Flexible Building Block to Improve the Scalability of a Wide Range of Graph Transformer Models Quick read: https://lnkd.in/gFiQyv8a Paper: https://lnkd.in/gsJqpi5F #machinelearning #ai

18

⭐️ New video release 📺: Performant, scientific computation in 🐍Python and 🦀 Rust Watch Stefan Ulbrich as he guides you through building performant scientific computation packages in Python and Rust, offering insights into efficient computation and optimization for machine learning and data science applications. 📺 Watch the video on YouTube: https://lnkd.in/eq-BhHdH Stefan Ulbrich, Senior Data Scientist, offers a tutorial on enhancing scientific computation in Python and Rust. The session explores packaging numerical calculus and algorithms using modern tools. Highlighting the efficiency of vectorization in Python for computational tasks within Machine Learning, Ulbrich presents the integration of Rust to optimize package performance. Rust, recognized for its performance and memory safety, complements Python, particularly for instances prioritizing speed and modern language features. The talk demonstrates creating a scientific Python package, gradually transitioning components to Rust for enhanced performance. Through an example of implementing the "Expectation maximization for Gaussian Mixture Models" algorithm, attendees learn how to leverage modern tools to build, optimize, and extend packages efficiently. Ulbrich emphasizes that while Rust knowledge is not mandatory, the session provides a high-level understanding of its benefits for Python extension and performance improvement. For a hands-on experience, participants are encouraged to clone Ulbrich's repository for swift installation and to optimize session time effectively.

9

1 Kommentar

👉🏼 A dataset of synthetic art dialogues with ChatGPT 🤓 Manuel Gil-Martín 👇🏻 https://lnkd.in/epWRbfCd 🔍 Focus on data insights: - 📊 The dataset comprises 13,870 synthetic dialogues, providing a rich resource for analyzing conversational dynamics in art discussions. - 🎨 It covers 799 distinct artworks and 378 different artists, allowing for diverse exploration of artistic themes and styles. - 🤖 High-quality dialogues were generated and assessed using both automatic and manual methods, ensuring reliability in the dataset's content. 💡 Main outcomes and implications: - 🔍 The dataset enables researchers to study emotional interventions and subjective opinions in art conversations, enhancing understanding of user engagement. - 📈 The evaluation metrics for detecting emotions achieved 92% accuracy, indicating strong potential for applications in sentiment analysis and AI-driven art education. - 🧠 The integration of various conversational roles (e.g., teacher-student) opens avenues for developing more interactive and personalized learning experiences in art. 📚 Field significance: - 🌐 This work contributes to the growing field of AI-generated content, particularly in the arts, by providing a unique dataset that bridges technology and creativity. - 💬 It highlights the importance of nuanced dialogue in understanding human-art interactions, paving the way for future research in art criticism and appreciation. - 🔗 The findings can inform the development of advanced conversational agents that facilitate deeper engagement with art, benefiting educators, students, and enthusiasts alike. 🗄️: [#syntheticdialogues] [#ChatGPT] [#art] [#dataset] [#emotionalinterventions] [#AI] [#education] [#sentimentanalysis] [#conversationalagents]

3

👋 We made some big announcements today at the #OSSummit! Here are the two new capabilities we announced: 1️⃣ Introducing the OSS Trust Graph, a way to model trust in open source ecosystems. It maps the connections between open source contributors and projects, and, through our “proof-of-diligence” algorithm, uses that data to build an understanding of the relative safety and sustainability of those projects. Read more about this and sign up for private beta access here: https://lnkd.in/gTWhvFN6 2️⃣ Announcing Minder Cloud: a fully managed version of Minder that makes it easier for open source developers and communities to set up and enforce policies to help them produce safer, more sustainable software. We have committed to making Minder Cloud FREE FOREVER for use on public repositories. 👍 Learn more and try Minder Cloud out now: https://lnkd.in/gfN3-Dd4

24

Is Postgres all you need? Is a vector just a data type? That's a tough question. On one hand, dedicated vector databases have a lot of catching up to do in terms of almost 30 years of functionality. On the other, there are advantages to reimagining the architecture factoring in all we know in 2024. The good news with txtai is that it's capable of working with multiple setups. It can persist data to Postgres. It can store data in Faiss + SQLite. It can also integrate content with other vector databases. The idea is to have everything needed to get started fast and be flexible to change as the requirements and landscape evolves. https://lnkd.in/dxWDeey

13

New blog post → Federated Learning in 10 lines of code, with PySyft 💨 This new tutorial explores how to implement #FederatedLearning (FL) using the latest features of #PySyft. We've enhanced our heart disease study with two new notebooks: one showcasing FL with Scikit-learn and a surprise bonus using #PyTorch! Don’t miss the opportunity to dive into this hands-on example and expand your skills in FL. Check it out and start your #datascience experiment today. 💡 👉 https://bit.ly/3U2IuNr

47

Introducing a new approach to graph-enabled RAG. LazyGraphRAG needs no prior summarization of source data, avoiding prohibitive up-front indexing costs. It’s inherently scalable in cost and quality across multiple methods and search mechanisms: https://lnkd.in/eMsfeiey

512

12 Kommentare

Did you know that some Large Language Models (LLMs) can suggest outdated and vulnerable Open Source Software (OSS) packages? This is because LLMs are often trained on static datasets that are only current up to a specific date, and don't receive dynamic patch updates. As a result, the OSS package recommendations generated by LLMs may include older versions with known security vulnerabilities that have since been fixed in newer versions. Recently, the Backslash Security Research Team conducted a study to investigate security gaps in AI-generated code from a developer's perspective. They created a series of simulations using GPT-4 and found critical security blindspots in AI-generated code, particularly in its use of third-party OSS. This highlights the importance of being aware of these potential security risks when using LLMs for code generation. How can we balance the benefits of using LLMs for code generation with the need to ensure the security and integrity of our applications? #ApplicationSecurity #DevSecOps #AIinSoftwareDevelopment #OpenSourceSecurity #LLMs #Cybersecurity

3

🌟 Revolutionizing RAG Systems with GraphRAG 🌟 Traditional Retrieval-Augmented Generation (RAG) systems often hit roadblocks when it comes to grasping deeper connections or handling large-scale context. That’s where GraphRAG steps in to transform the game entirely. 🚀 🔍 What Sets GraphRAG Apart? 1️⃣ Context Across Multiple Scales With GraphRAG, it’s not just about isolated chunks of text anymore. This system creates summaries at various levels—from detailed breakdowns of paragraphs to high-level document overviews. Think of it as giving your AI the full map instead of just a snapshot. Whether summarizing an entire book or analyzing a chapter, GraphRAG ensures the context is rich and layered. 2️⃣ Visualizing Knowledge with Graphs Why stick to linear text? GraphRAG converts information into a knowledge graph, showcasing entities (nodes) and their relationships (edges). For instance, a sentence like: “John Smith teaches Mathematics at Oxford and has 15 years of experience” becomes a clear graph that connects “John Smith” to “Mathematics,” “Oxford,” and “15 years of experience.” This structured approach makes complex information retrieval seamless. 3️⃣ Smarter Chunking for Better Results No more fragmented ideas or disconnected pronouns! GraphRAG intelligently chunks and links related information to preserve narratives and context. For example: Chunk 1: “Billy went to the store yesterday afternoon.” Chunk 2: “He bought some groceries and milk.” GraphRAG ensures these ideas stay connected, making retrieval accurate and meaningful. 🔗 Why You Can’t Miss Out GraphRAG is rewriting the rules of knowledge retrieval with: ✔️ Enhanced context through multi-scale summaries. ✔️ Clear, structured relationships via knowledge graphs. ✔️ Intelligent grouping of data for coherent retrieval. Whether you're diving into massive datasets, tackling intricate questions, or summarizing vast documents, GraphRAG unlocks the power of deeper understanding and smarter AI systems. 💡 Ready to experience the next level of RAG systems? Don’t wait to explore GraphRAG—stay ahead in the world of AI innovation! What’s your take on this? Are you already envisioning its potential in your work? #GraphRAG #AIInnovation #KnowledgeGraph #LLMs #MachineLearning

5

2 Kommentare

🚀 Looking to streamline fine-tuning for models like Llama 3, Mistral, and Mixtral? Our latest blog shows how Anyscale simplifies LLMs fine-tuning with Ray: 🔑 Key takeaways: • Scalable fine-tuning with LLM-Forge • Model Deployment with RayLLM Read more: https://lnkd.in/gQwD4A2U

35

Retrieval-Augmented Generation (RAG) enables answering functional, technical and domain-related questions about large codebases using LLMs, thus supporting developers in onboarding, feature development, or error analysis. In traditional RAG, code fragments relevant to the query are selected using similarity search. However, this method can miss critical code segments that are not directly related to the query but are crucial for correctly answering the question. As part of her master's thesis at itestra, Helena is researching an extension of RAG with enhanced code retrieval capabilities based on LLM agents. This aims to deliver more precise code snippets, significantly improving the quality of the answers. Helena uses Llama 3 70B and runs the entire setup on-premise on our own Nvidia RTX 6000 Ada, making it suitable for projects where the source code should not be processed in the cloud. #SoftwareEngineering #CodeAnalysis #ArtificialIntelligence #GenerativeAI #RetrievalAugmentedGeneration #LargeLanguageModel

28

4 Kommentare

Learn the best strategies for selecting a group of nodes with the highest combined influence on the graph — Eivind Kjosbakken provides a clear and detailed explanation in his in-depth tutorial.

7