grh.mur.at

New project: auphonic

grh — Wed, 06 Jul 2011 16:19:43 +0000

Currently I am working on the auphonic project, which involves machine learning, audio signal processing, web development, open-source technologies and much more.

So don't expect many updates on my mur.at page, I will write about new things on the auphonic blog. You can subscribe to the auphonic feed or follow @auphonic on twitter.

Pure Data workshop at the Metalab

grh — Sun, 07 Nov 2010 19:47:16 +0000

Date:

29. January 2011 - 30. January 2011

City:

Vienna

Country:

Austria

Event Description:

Two days, free Pure Data workshop at the Metalab (www.metalab.at) in Vienna !

See the workshop WIKI page for further information: http://metalab.at/wiki/Pd-Workshop !

Android 2.2 on an old HTC Magic (32B)

grh — Sun, 26 Sep 2010 10:33:47 +0000

Because of the bad weather I tried to update my old HTC Magic phone to the new Android 2.2 today: I wanted to have the latest and greatest Android features . However, some tweaks were necessary to get a real nice performance. One has to go through long forum posts to optimize the system etc., therefore here is a short summary. (These tips might be also helpful on other old phones, like the G1)
But it's worth the hassle: now the HTC Magic feels like an expensive, recent Desire phone !

Installing the system

How to become a Pure Data / GEM Professional

grh — Sun, 20 Jun 2010 18:31:49 +0000

These are materials from a lecture about realtime audio and video programming (using GEM and Pure Data) at the University of Applied Science, FH Joanneum, for the master programme Media and Interaction Design.

Lecture: Audio/Video Programming with Pure Data

grh — Tue, 15 Jun 2010 20:47:02 +0000

Date:

17. June 2010 - 21. June 2010

City:

Graz

Country:

Austria

Event Description:

I will give a lecture for realtime video programming (using GEM and Pure Data) at the University of Applied Science, FH Joanneum, for the master programme Media and Interaction Design.
The materials are online at How to become a Pure Data / GEM professional.

Chaos Communication Congress in Eibiswald

grh — Thu, 24 Dec 2009 14:10:18 +0000

Der Chaos Communication Congress 26C3 ist ein mehrtägiges Treffen der internationalen Hackerszene, organisiert vom Chaos Computer Club. Der Kongress findet heuer vom 27. bis 30. Dezember in Berlin statt und widmet sich in zahlreichen Vorträgen und Workshops technischen und gesellschaftspolitischen Themen.

Tethering Script for Android Phones and Gnome

grh — Tue, 03 Nov 2009 15:45:35 +0000

Update: If you want to use _real_ tethering (without proxy), install CyanogenMod - a tutorial is in the Wiki !

Just a small shell script to get an internet connection on a standard gnome desktop (e.g. Ubuntu) via a proxy on an android phone (no root access needed!).

champions @ Piksel Festival Bergen

grh — Sat, 10 Oct 2009 07:13:05 +0000

Date:

19. November 2009 - 22. November 2009

City:

Bergen

Country:

Norway

Event Description:

In our tour with the champions (Georg Holzmann (champion), Michi Pinter(champion), IOhannes m zmölnig (champion)) we will make the next stop at the Piksel Festival in Bergen.

Hope to see you there !

Advanced Psychoacoustics 2: Silent Subliminals

grh — Fri, 18 Sep 2009 14:05:04 +0000

Do you want to influence a humans behavior ?
Or maybe induce some thoughts in the brain of all people listening to a specific radio channel ?
Then you found the right blog entry, which will present you a Pure Data program to change the attitude of your desired audience ...

Echo State Networks with Filter Neurons and a Delay&Sum Readout

grh — Mon, 13 Jul 2009 17:05:14 +0000

Year:

2010

Authors:

Georg Holzmann

Authors:

Helmut Hauser

Type:

Journal paper

Publisher:

Neural Networks

Abstract:

Echo state networks (ESNs) are a novel approach to recurrent neural network training with the advantage of a very simple and linear learning algorithm. It has been demonstrated that ESNs outperform other methods on a number of benchmark tasks. Although the approach is appealing, there are still some inherent limitations in the original formulation.

Here we suggest two enhancements of this network model.
First, the previously proposed idea of filters in neurons is extended to arbitrary infinite impulse response (IIR) filter neurons. This enables such networks to learn multiple attractors and signals at different timescales, which is especially important for modeling real-world time series.
Second, a delay&sum readout is introduced, which adds trainable delays in the synaptic connections of output neurons and therefore vastly improves the memory capacity of echo state networks.

It is shown in commonly used benchmark tasks and real-world examples, that this new structure is able to significantly outperform standard ESNs and other state-of-the-art models for nonlinear dynamical system modeling.

Publication:

Echo State Networks with Filter Neurons and a Delay&Sum Readout (preprint)