Causality vs Correlation: Granger Causality

One of the most repeated mantra’s of Machine Learning is that “A Causation is not a Correlation!” When faced with … More

Advances in Convex NMF: Linear Programming

Today I am going to look at a very important advance in one of my favorite Machine Learning algorithms, NMF … More

cloud-crawler : an open source ruby dsl and distributed processing framework for crawling the web using aws

cloud-crawler-0.1 For the past few weeks, I have taken some time off from pure math to work on an open … More

Foundations: Theory of Compressed Sensing

Introduction: In an much earlier post, we looked at detecting Gravity Waves using Machine Learning and techniques like Minimum Path … More

Noisy Time Series II: Earth Quakes, Black Holes, and Machine Learning

Recently , 7 Italian Scientists have been sentenced in prison for manslaughter for failing to predict an Earthquake in 2009 ! … More

Modeling Noisy Time Series: Least Squares Spectral Analysis

Today we consider the problem of modeling periodic behavior in a noisy time series. This is an old problem from … More

Data Spectroscopy: Gaussian Kernels and Harmonic Oscillators

Previously we developed some intuition behind the Radial Basis Function / Gaussian Kernel by looking at its Fourier components. We learned that … More

Spectral Clustering: A quick overview

A lot of my ideas about Machine Learning come from Quantum Mechanical Perturbation Theory. To provide some context, we need … More

Kernels, Green’s Functions, and Resolvent Operators

Machine Learning uses Kernels. At least it tries when it can. A Kernel is an operator on a Hilbert Space. … More

Eigenvalue-Independent Effective (Semantic) Operator

This post is still just sketch of ideas…not ready for consumption In my last post I introduced the Eigenvalue-Dependent Effective (Semantic) … More