In my previous article, I discussed how morphological feature extractors mimic the way biological experts visually assess images. time, I want to go a step further and explore a new question:Can different architectures complement each other to build an AI that “sees” like an expert? Introduction: Rethinking Model Architecture Design While building a high accuracy …
Building a responsible approach to data collection with the Partnership on AI At DeepMind, our goal is to make sure everything we do meets the highest standards of safety and ethics, in line with our Operating Principles. One of the most important places this starts with is how we collect our data. In the past …
Why build things the hard way when you can design them the smart way? As a Supply Chain Data Scientist, I’ve explored various frameworks like LangChain and LangGraph to build AI agents using Python. Leveraging LLMs with LangChain for Supply Chain Analytics — A Control Tower Powered by GPT — (Image by Samir Saci) The illustration above is from an …
Automate Supply Chain Analytics Workflows with AI Agents using n8n Read More »
Today we’re introducing Gemini 2.5, our most intelligent AI model. Our first 2.5 release is an experimental version of 2.5 Pro, which is state-of-the-art on a wide range of benchmarks and debuts at #1 on LMArena by a significant margin. Gemini 2.5 models are thinking models, capable of reasoning through their thoughts before responding, resulting …
0. Least Squares is used almost everywhere when it comes to numerical optimization and regression tasks in machine learning. It aims at minimizing the Mean Squared Error (MSE) of a given model. Both L1 (sum of absolute values) and L2 (sum of squares) norms offer an intuitive way to sum signed errors while preventing them …
Least Squares: Where Convenience Meets Optimality Read More »
Notes References [1] John M Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ron-neberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin Zídek, Anna Potapenko, Alex Bridgland, Clemens Meyer, Simon A A Kohl, Andy Ballard, Andrew Cowie, Bernardino Romera-Paredes, Stanislav Nikolov, Rishub Jain, Jonas Adler, Trevor Back, Stig Petersen, David A. Reiman, Ellen Clancy, Michal Zielinski, …
Benchmarking the next generation of never-ending learners Read More »
previous article on organizing for AI (link), we looked at how the interplay between three key dimensions — ownership of outcomes, outsourcing of staff, and the geographical proximity of team members — can yield a variety of organizational archetypes for implementing strategic AI initiatives, each implying a different twist to the product operating model. Now …
Evolving Product Operating Models in the Age of AI Read More »
Notes [1] Abramson, J., Ahuja, A., Barr, I., Brussee, A., Carnevale, F., Cassin, M., Chhaparia, R., Clark, S., Damoc, B., Dudzik, A. and Georgiev, P., 2020. Imitating interactive intelligence. arXiv preprint arXiv:2012.05672. [2] Abramson, J., Ahuja, A., Brussee, A., Carnevale, F., Cassin, M., Fischer, F., Georgiev, P., Goldin, A., Harley, T. and Hill, F., 2021. …
Building interactive agents in video game worlds Read More »
With the new age of problem-solving augmented by Large Language Models (LLMs), only a handful of problems remain that have subpar solutions. Most classification problems (at a PoC level) can be solved by leveraging LLMs at 70–90% Precision/F1 with just good prompt engineering techniques, as well as adaptive in-context-learning (ICL) examples. What happens when you …
R.E.D.: Scaling Text Classification with Expert Delegation Read More »
Join Nolan Fortman and Logan Kilpatrick for a deep conversation with Dwarkesh Patel, host of the Dwarkesh podcast, and one of the 2024 TIME most influential people in AI. We chat about how the world is going to change with AI in the next 2 years, infinite AI dimensionality, creating content for the AI world, …
