In this article, we present a parametric cellular-automata framework that makes it easy to build simulators and analysis tools for a wide range of automata.
Promptheon is an LLM-powered system for exploring and structuring knowledge about ancient deities from Wikipedia. The project begins by crawling the List of Deities category page, using a Gemini-based language model to classify portal links by cultural origin or divine role. Each portal is then crawled to extract linked pages, which are filtered by another LLM call to retain only deity-related entries.
This article presents a collection of mind maps that illustrate key machine learning (ML) concepts and algorithms. Where relevant, it highlights commonly used ML libraries, packages, classes, and functions—with a particular focus on components from the Scikit-learn library.
We have previously explored two multi-armed bandit (MAB) strategies: Maximum Average Reward (MAR) and Upper Confidence Bound (UCB). Both approaches rely on the observed average reward to determine which arm to pull next, using a deterministic scoring mechanism for decision-making.
In this article, I will explore the balance between exploration and exploitation, a key concept in reinforcement learning and optimization problems. To illustrate this, I will use the multi-armed bandit problem as an example. I will also explain how the epsilon-greedy strategy effectively manages this balance.
In a previous article, I introduced the design and implementation of a multi-armed bandit (MAB) framework. This framework was built to simplify the implementation of new MAB strategies and provide a structured approach for their analysis.
In previous blog posts, we explored the multi-armed bandit (MAB) problem and discussed the Upper Confidence Bound (UCB) algorithm as one approach to solving it. Research literature has introduced multiple algorithms for tackling this problem, and there is always room for experimenting with new ideas. To facilitate the implementation and comparison of different algorithms, we introduce a framework for MAB solvers.