Jason Mora

Regardless of your specific role in data science or machine learning, data parsing and processing are likely part of your regular workflow — and Ilija Lazarevic explains how you can leverage open-source library Pydantic to execute them more smoothly and effectively.

23

SHLee AI Financial Model delivers a tutorial on using SAS for estimating regression models: https://lnkd.in/es98R4re #Econometrics

1

Want to crush your next interview? 💥 Start here with these Retrieval-Augmented Generation (RAG) interview questions! A must-read for data pros looking to stand out. 🖇️https://ow.ly/khoM50Tu81k #DataCamp #DataScience #MachineLearning

44

1 Comment

Models like OpenAI's CLIP combine text and images for search, but they have limitations, particularly with longer texts and complex relationships. This article talks about JINA's new model that improves on CLIP by integrating both text and image embeddings in one model, making it faster and more efficient for multimodal search tasks. Experiments and Findings: → Search with Both Text and Images: Combining both embeddings leads to better and more diverse search results, improving relevance and variety in results. → Image-Driven Diversification: By using images for diversification, Jina-CLIP v1 can present a broader range of results, offering users more varied options. Results Comparison: → Using both text and image embeddings (via averaging) consistently outperformed searches based solely on text or images, providing more precise and diverse retrieval across both broad and fine-grained categories. https://lnkd.in/guNRQpBU

15

Thank you for sharing this fascinating prediction and breakdown! 🌟 Your focus on multi-attribute vector indexes that combine tabular and unstructured data strikes a chord with the growing need for more adaptable and context-aware retrieval systems. 🚀 I completely agree with your assertion that tabular data dominates many practical applications like search, analytics, and retrieval systems. Leveraging structured data alongside unstructured formats (text, images, audio) for semantic search is a natural evolution and addresses a significant gap in current retrieval technologies. 🔍 Your emphasis on avoiding text-to-SQL is a refreshing perspective. Instead of adding layers of complexity, building semantic capabilities directly into multi-attribute vector spaces offers a more streamlined and intuitive solution for search and retrieval systems. 💡 The step-by-step guide for creating a vector index, particularly for e-commerce products, is spot on. Treating each table row as a node and focusing on vector similarity spaces between attributes like product descriptions, prices, and reviews is a practical and scalable approach for enhancing search relevance. 🛍️✨ The ability to customize searches by weighting semantic attributes is a game-changer. This flexibility enables businesses to optimize retrieval results based on user preferences (e.g., balancing affordability with quality), which is crucial for improving user satisfaction and conversion rates. Your use of Superlinked and MongoDB Atlas demonstrates how existing tools can be leveraged effectively to create sophisticated retrieval systems. It’s inspiring to see how these ideas can be implemented with accessible technologies. Thank you for sharing these insights! I’m excited to see how your prediction plays out in 2025 and beyond. Would love to dive deeper into the weighted attribute approach you’ve hinted at for a future discussion! 🙌 #RAG #SemanticSearch #AIInnovation #VectorIndexes #DataEngineering #FutureOfSearch

7

Meta AI is making big changes to how large language models (LLMs) work, and competition from open-source models like Qwen and Deepseek is fueling this innovation. - They're working on something called Large Concept Models (LCMs). Instead of looking at words one by one, these models look at whole ideas at once. This could help them understand things better and write more smoothly. (https://lnkd.in/gm55C2wW) - They also have a new trick called EWE. This gives LLMs a kind of "scratchpad" memory. This helps them check their facts as they write, so they make fewer mistakes. (https://lnkd.in/gk5fTpKY) Putting these two things together could mean LLMs that write more accurate and smarter text, perhaps (?) closer to how humans think.

118

3 Comments

"Prompt Engineering" by Lee Boonstra. This paper covers everything from basic prompting techniques to advanced strategies like Chain of Thought (CoT), Tree of Thoughts (ToT), and ReAct, along with practical tips for code-related prompting. Key sections include: - Configuring output with temperature, top-K, and top-P settings - Using zero-shot, one-shot, and few-shot prompting effectively - System, role, and contextual prompting techniques - Best practices, including experimenting with input formats and adapting prompts to model updates https://lnkd.in/gH5xrivh

13

An underrated component of RAG evals is retrieval evals - is potentially more important than LLM evals! Some requirements for performing retrieval evals is 1) identifying the right retrieval metrics, and 2) having a unified dataset representation. This article by Ross Ashman takes you through tour of retrieval/ranking metrics (e.g. precision@K, NDCG, and more), and also shows you how to convert a dataset into the BEIR format in order to run these evals. Once retrieval evals is setup, run it over your LlamaIndex retrievers. https://lnkd.in/gfha8kiX

173

3 Comments

Diving into the world of regression, Samy Baladram explores the Nearest Neighbor Regressor. As datasets grow, efficiently finding neighbors is key. Enter KD Trees and Ball Trees. #MachineLearning #DataScience

14

Overfitting in ML: Why It Matters Overfitting happens when a model is too focused on training data, causing poor real-world performance. Stay aware to get more accurate predictions. Read more : https://lnkd.in/gNcyi_x #datascience #machinelearning #overfitting #ai #bigdata #mlalgorithms #techinsights #deeplearning #artificialintelligence #datamodeling #dataanalytics #linkedin #youtube #twitteonx #threads #instagram #like #share #sprintzeal #sprintzealcommunity

2

1 Comment

It's a question that often comes up in discussions about the role of data scientists. The short answer is: Yes, but it's more nuanced than that. Data scientists do code, but their focus isn't solely on writing perfect, production-level code like a software engineer. Instead, they leverage coding to explore data, build models, and extract insights that drive business decisions. Here’s how coding fits into a data scientist's role: 1. Data Manipulation: Data scientists use coding languages like Python, R, and SQL to clean, manipulate, and analyze large datasets. This involves tasks like handling missing values, transforming data formats, and merging datasets. 2. Model Building: Coding is essential when creating predictive models. Data scientists often use libraries like TensorFlow, scikit-learn, or Keras to build and train machine learning models. 3. Automation: To make their workflows efficient, data scientists write scripts to automate repetitive tasks, such as data extraction, transformation, and loading (ETL). 4. Visualization: Coding helps in creating insightful visualizations. Tools like Matplotlib, Seaborn, and Plotly allow data scientists to code and generate graphs and dashboards that communicate their findings effectively. 5. Collaboration with Engineers: While data scientists do code, their work must be integrated into a larger system. This is where collaboration with data engineers and software developers comes into play. Knowing how to code enables smoother communication and integration of their models into production environments. So, do data scientists code? Absolutely! But their coding is a means to an end—analyzing data, building models, and driving insights—not an end in itself. https://lnkd.in/g_6BPxtm https://lnkd.in/gJiDyQDN #DataScience #Coding #MachineLearning #Python #BigData #Analytics #ArtificialIntelligence #DataVisualization #TechCareers #DataScienceLife #DataScientists

4

I came across an excellent GitHub repository packed with hands-on Jupyter notebooks for anyone eager to explore LLMs. It covers: 🔹 Introduction to LLMs – Understanding the basics. 🔹 Tokens & Embeddings – The foundation of language modeling. 🔹 Model Internals – Peeking under the hood of LLMs. 🔹 Text Applications – Classification, clustering, and topic modeling. 🔹 Prompt Engineering – Crafting prompts for better performance. 🔹 Advanced Text Generation – Tools and techniques. 🔹 Semantic Search – Intelligent information retrieval. 🔹 Multimodal Models – Combining text and image understanding. 🔹 Customization – Building embeddings, fine-tuning BERT, and generative models. Big thanks to the repo creator for sharing such a valuable resource. Here is the repo: https://lnkd.in/gUKg7Jp7

77

2 Comments

Valeriy Manokhin, PhD, MBA, CQF, I attended the Pydata conference back in 2016 and your recent post on the Dempster Shaffer method caught my attention. It brought to mind the valuable insights shared by Taposh Dutta Roy and Austin Powell from KP on this topic. If you're interested, you can find more details in this video: https://lnkd.in/gmegrbTb Love your posts Valeriy Manokhin, PhD, MBA, CQF keep them coming! #pydata

7

1 Comment

Why wait for slow queries when you can speed things up? On the Apache Arrow blog, Ian Cook, David Li, and Matt Topol, break down how Arrow's format accelerates query result transfers by eliminating inefficiencies. Key takeaways: ✅ Columnar format reduces costly transpositions ✅ Zero-copy architecture minimizes overhead ✅ Universal language support ensures seamless integration across platforms Read the full post to learn how Arrow boosts query performance and discover real-world speedups from tools like Theseus, DuckDB, and Snowflake. 🔗 Read more: https://lnkd.in/eBbjz5uZ #DataAnalytics #ApacheArrow #BigData #OpenSource

18

Linear models can handle non-linear relationships thanks to data pre-processing. But how close can they get to more sophisticated models? 🤔 Check out Samuele Mazzanti's newest article for more! #MachineLearning #DataScience

31

1 Comment

I really liked reading this article as it provides an insightful explanation of quantization, a technique commonly used in machine learning to simplify models. It covers key concepts such as scalar and vector quantization, and illustrates their practical applications (Quantization-Aware Training (QAT), Post-Training Quantization (PTQ)) with clear visuals. https://lnkd.in/gYKw3PDu

23