<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>CacheNova</title><description>Writings about AI, maths, programming, and my curiosity about the world.</description><link>https://cachenova.github.io/</link><item><title>Learning to Simulate: The Idea Behind My Undergrad Research</title><link>https://cachenova.github.io/posts/learning-to-simulate-the-idea-behind-my-undergrad-research/</link><guid isPermaLink="true">https://cachenova.github.io/posts/learning-to-simulate-the-idea-behind-my-undergrad-research/</guid><description>A reflective write-up on simulating the concept behind my undergraduate research and why it matters for learning and experimentation.</description><pubDate>Sat, 25 Apr 2026 18:00:00 GMT</pubDate></item><item><title>Tensors: The Bricks of PyTorch</title><link>https://cachenova.github.io/posts/tensors-the-bricks-of-pytorch/</link><guid isPermaLink="true">https://cachenova.github.io/posts/tensors-the-bricks-of-pytorch/</guid><description>A structured introduction to tensors in PyTorch, covering storage, dtype, view, shape, stride, and offset as the core ideas behind how tensors work.</description><pubDate>Sun, 19 Apr 2026 18:00:00 GMT</pubDate></item><item><title>Learning CUDA Through Matrix Multiplication</title><link>https://cachenova.github.io/posts/learning-cuda-through-matrix-multiplication/</link><guid isPermaLink="true">https://cachenova.github.io/posts/learning-cuda-through-matrix-multiplication/</guid><description>A personal walkthrough of finally trying CUDA with matrix multiplication, how the thread mapping works, and how I profiled it against NumPy in a Colab-friendly setup.</description><pubDate>Sun, 12 Apr 2026 18:00:00 GMT</pubDate></item><item><title>Compressing Reality: A PCA Deep Dive</title><link>https://cachenova.github.io/posts/lit-lab/compressing-reality-a-pca-deep-dive/</link><guid isPermaLink="true">https://cachenova.github.io/posts/lit-lab/compressing-reality-a-pca-deep-dive/</guid><description>A practical guide to Principal Component Analysis (PCA) covering the intuition, mathematical foundations, and a step-by-step implementation. Learn how PCA performs dimensionality reduction and why it is widely used in machine learning and data analysis.</description><pubDate>Sun, 05 Apr 2026 16:40:00 GMT</pubDate></item></channel></rss>