johnramey

Python for Statistical Computing

MetaOptimize - A Machine Learning Q&A Community (Similar to StackOverflow)

Using bootstrap in cluster analysis

Git Magic – A Git Tutorial as a Video Game Analogy

Bayesian Reasoning and Machine Learning – Textbook with free online textbook (in beta) by David Barber.

Bioconductor Experiment Data Packages – A list of packages with experiment data (a lot of microarray)

Bioconductor One-day Overview Course – From Harvard Biostatistics Department (PDF)

Clustering and Visualization of Microarray Data – This is the best presentation I have seen of the topics, including clustering evaluation (PDF)

Statistical Microarray Data Analysis – This excellent presentation from the same guy includes the one above and discusses a much broader scope. (PDF)

Han-Ming Wu’s Site – This is the professor that released the above two presentations. He has more information on his site. (Only some English)

Very slick poster with ggplot2 graphics – Note the github project at the bottom.

Concentrations of Measure – This is Prof. Tyrone Vincent’s great presentation on probability inequalities from PASI

Machine Learning Video Lectures and Notes – Professor Tom Mitchell at Carnegie Mellon

Bayesian Statistics – Scholarpedia Entry (Recommended by Prof. Andrew Gelman)

A Large Collection of Notes on Stochastic Processes

My Question on Stack Exchange about Lagrange Multipliers with Inequality Constraints

One-liners which make me love R: Make your data dance (Hans Rosling style) with googleVis

Response Surface Plot Example in R with rgl

Excellent Set of ‘Data Mining’ Notes from Professor Shalizi at Carnegie Mellon

Annotated Computer Vision Bibliography – A HUGE list of links from various disciplines related to pattern recognition, machine learning, facial recognition, etc. Highly recommended for exploration.

A paper from Strimmer Lab that discusses James-Stein  shrinkage estimators related to one of my papers

Fast SVD for Large-Scale Matrices

Spectral Variation, Normal Matrices, and Finsler Geometry - Provides a great discussion on the development of the Hoffman-Wielandt theorem and describes several inequalities related to the Frobenius norm of the difference of two matrices

A Note on the Hoffman-Wielandt Theorem for Generalized Eigenvalue Problem - An interesting development of diagonalizable pairs of Hermitian matrices.

Seminar Materials for Bayesian Reinforcement Learning

 The Shame of College Sports – An article that has been highly recommended to me about corruption in college sports

UCSDs Computational Mass Spec Blog – I like how they compile papers and comment on them in blog form with various details about each. I am tempted to adopt their method.

Extending and Embedding R with C++ – Presentation

Mommy, I found it! — 15 Practical Linux Find Command Examples

Introduction to Machine Learning – book by Alex Smola (Yahoo)

Applied Multivariate Statistical Analysis – Excellent book by Hardle and Simar (PDF!)

Primer on Matrix Analysis and Linear Models – Excellent resource for more rigorous approach to matrices!!!

Applied Statistics for Bioinformatics using R – Book (PDF)

Distributed Computing with R Using Snowfall – Presentation (PDF)

How can you learn mathematics for machine learning? - Quora

What are some good resources for machine learning? – Quora

Introduction to Neural Networks – comp.ai.neural-nets newsgroup

Statistical Data Mining Tutorials – Slides by Prof. Andrew Moore at CMU

Accuracy of pseudo-inverse covariance learning – a Random Matrix Theory Analysis (peaking effect!)

Machine Learning Data Set Repository

Material for Jieping Ye’s Machine Learning Course – Lots of papers, links, data sets, and tutorials.

Data sets from “Elements of Statistical Learning”

Benchmark Data Sets for Supervised Classification

Rosetta Code (Translation of Various Coding Tasks into Many Programming Languages)

Visualizing Growth of a Retail Chain in R

StackOverflow – How to efficiently use Rprof in R?

A Random Matrix-Theoretic Approach to Handling Singular Covariance Estimates

Shrinkage Discriminant Analysis and Feature Selection (along with sda package on CRAN)

Bayesian Model Averaging: A Tutorial (PDF)

Statistical Learning Based on High Dimensional Data (PDF: Master’s Thesis focused on Regularized Discriminant Analysis)

Objective Bayesian Analysis of Kullback-Liebler Divergence of Two Multivariate Normal Distributions with Common CovarianceMatrix and Star-shape Gaussian Graphical Model (PDF: Dissertation)

Quasi-Likelihood

Probabilistic Modeling with WinBugs

Large Collection of Facial Recognition Databases, Papers, and Algorithms

Microarray data analysis: from disarray to consolidation and consensus

Accounting for Computer Scientists

Genetic Algorithm for Hello World

Five ways to visualize your pairwise comparisons (in R)

Cross-Validation and Mean-Square Stability

Pennant (iOS App for Displaying and Visualizing Baseball Data)

I am terrible about leaving tabs open in Google Chrome.  Often I find useful links, which are related (whether directly or indirectly) to my current project, but in order to get anything done right now, I have to push these off onto a stack. My stack of choice is opening a new tab. As I open more and more tabs without ever returning to the previous ones, Chrome becomes bogged down, sluggish, and filled with many potential distractions.

I currently have 3 Chrome windows open with a total of 20 tabs present. As an example, below is a screenshot of the tabs from one window.

At one point, InstaPaper was my fix for this problem. If I encountered a new link (that are really Internet shine-ys), my first response was to stuff the link quickly into my InstaPaper account through the nice icon on my address bar. My InstaPaper account became a huge repository of links that I wanted to read and to understand. Unfortunately, when a mass collection resulted, I became more unlikely to return to them.

Recently, through my Twitter account, I encountered John D. Cook’s blog and noticed his Weekend miscellany. It seems that he has a decent way of dealing with useful but potentially distracting links. Although this may not be his motivation, I am interpreting this as a temporary delay in dealing with a link with the goal of returning to them at a set time, say the weekend. I have decided I am going to do much the same thing and beginning something I am naming Wait til the Weekend.

Here are my first links:

Visualization of Support Vector Machines with Polynomial Kernels

Advanced R Development

Generalized Eigenvalue Decomposition in C#

Handwriting Recognition using Kernel Discriminant Analysis

Generalized Linear Model Notes