Deep Dives
Artificial Intelligence
Making a Data Pipeline to Monitor Local Crime Trends
about examining crime trends in your local area. You recognize that relevant data exists, and you might have some basic analytical skills which you can use to research this data. Nonetheless, this data...
Artificial Intelligence
Routing in a Sparse Graph: a Distributed Q-Learning Approach
concerning the Small-World Experiment, conducted by Stanley Milgram within the 1960’s. He devised an experiment by which a letter was given to a volunteer person in the US, with the instruction to forward...
Artificial Intelligence
On the Possibility of Small Networks for Physics-Informed Learning
Introduction
within the period of 2017-2019, physics-informed neural networks (PINNs) have been a very talked-about area of research within the scientific machine learning (SciML) community . PINNs are used to unravel atypical and partial...
Artificial Intelligence
Why Your Multi-Agent System is Failing: Escaping the 17x Error Trap of the “Bag of Agents”
landed on arXiv just before Christmas 2025, very much an early present from the team at Google DeepMind, with the title “Towards a Science of Scaling Agent Systems.” I discovered this paper to be a...
Artificial Intelligence
Federated Learning, Part 2: Implementation with the Flower Framework 🌼
within the federated learning series I'm doing, and should you just landed here, I might recommend going through the primary part where we discussed how federated learning works at a high level. For...
Artificial Intelligence
Modeling Urban Walking Risk Using Spatial-Temporal Machine Learning
After dinner in downtown San Francisco, I said goodbye to friends and pulled out my phone to work out how you can get home. It was near 11:30 pm, and Uber estimates were unusually...
Artificial Intelligence
From Connections to Meaning: Why Heterogeneous Graph Transformers (HGT) Change Demand Forecasting
forecasting errors are usually not brought on by bad time-series models.
They're brought on by ignoring structure.
SKUs don't behave independently. They interact through shared plants, product groups, warehouses, and storage locations. A requirement shock...
Artificial Intelligence
Going Beyond the Context Window: Recursive Language Models in Motion
, context really is every thing. The standard of an LLM’s output is tightly linked to the standard and amount of knowledge you provide. In practice, many real-world use cases include massive contexts: code...
Recent posts
