Charlie's Blog

Verdena @ Majano 2011.

carlocomin — Thu, 11 Aug 2011 12:14:31 +0000

Yesterday I’ve seen Verdena live in Majano Udine, I was togheter with some good friends.

I can’t put this gig into words, hence I’ve uploaded some media on youtube!

Thank you guys!

.bashrc in OSX 10.6

carlocomin — Fri, 29 Jul 2011 19:18:29 +0000

It is unbelievable how OSX 10.6 comes without .bashrc by default.
To enable it, just add the string
[ -r $HOME/.bashrc ] && source $HOME/.bashrc
to your /etc/profile.

How to catch a signal.

carlocomin — Tue, 19 Apr 2011 09:49:31 +0000

Simple signal catcher example: signal.c

KmemGuard

carlocomin — Thu, 06 Jan 2011 16:46:36 +0000

KmemGuard is a tool I wrote for Linux Kernel 2.6.7., when the S.P.I.N.E. project was still alive. It protects and eventually repairs the syscalltable using /dev/kmem. One can use it as a first countermeasure against malicious syscalltable injections, often performed by rootkits. As a proof of concept, it is usable although by no means complete.

I’ll test it on recent kernel releases soon… in the meantime, here it is for Linux 2.6.7. kmemguard.c

Gridworld v0.2

carlocomin — Wed, 29 Sep 2010 15:27:08 +0000

Change List:

* Multipolicy visualization – added

* Input integrity check – added

GridWorld .java .jar

GridWorld + Reinforcement Learning

carlocomin — Fri, 24 Sep 2010 14:56:02 +0000

I’ve developed a Java+Swing+Awt code for GridWorld (cfr. Barto-Sutton 1998). It implements the Value Iteration Reinforcement Learning algorithm. Enjoy!

.java .jar

Maximum likelihood is equivalent to least squares in the presence of Gaussian noise

carlocomin — Wed, 01 Sep 2010 14:21:04 +0000

Studying machine learning and statistical pattern recognition these days, I’ve learned a nice fact about estimation. The proof is straightforward but I’d like to remeber this fact, so here it is.

Note. Maximum likelihood estimation is equivalent to least squares estimation in the presence of Gaussian noise.

Let and let follow a normal gaussian distribution .

In a least squares estimate one minimize the following

(*)

In a maximum likelihood one defines a likelihood

and then minimize

which is equivalent to (*). QED

Hello World.

carlocomin — Wed, 25 Aug 2010 16:41:50 +0000

Hello World . So… uhm… this is my first post on this blog I plan to post regularly sharing links of interest and posting my works (such as source codes, math and cs proofs, papers, etc…). Up until now, this Blog is intended as a personal repository and online diary. But… hey, no one knows… if you find something interesting here, feel free to leave a comment.

Ok then… stay tuned .