Imagine you're blindfolded on a mountainside, trying to find the lowest valley. You can only feel the slope beneath your feet and take one step at a time. How would you navigate to the bottom? This ...

Abstract: Conventional loss functions for gradient descent are designed mainly to assess output quality, with limited attention to gradient behavior. This study identifies the gradient inconsistency ...

Sometimes we want to optimise functions that are hard to optimise. Here are two examples: $$f(x) = \text{sinc}(x) \quad \text{and} \quad f(x) = \lfloor 10 \cdot \text ...

This project provides a basic implementation of a decision tree and tree-based ensemble learning algorithms like random forest and gradient boosting machines from scratch, aimed at helping developers ...