By offering automated information extraction tools from data, machine learning has revolutionized the way in which humans can cope with electronic data volumes. The ever increasing complexity of the settings continues to pose challenges to the field: often, it is no longer possible to specify a priori a formal learning task; complex parameter choices can severely influence the outcome; and an appropriate encoding of data is not clear at all. More and more often, the human constitutes an important step in the loop to interactively decide about an appropriate learning model, model parameters, and data representation. Because of this fact, intuitive models and model parameters, and human understandable interfaces to the model and data are needed. In this frame, interesting new technologies have been developed such as high quality data visualization tools, sparse interpretable data representation and models, informed priors, active learning, and similar.

This special session aims to foster research in neural learning paradigms which offer an intuitive interface to data or models and thus have the potential as parts of an interactive pipeline. Go to the special session web site more information.

Organisers: Oliver Obst, Mikhail Prokopenko (CSIRO ICT Centre)

Keynote speaker (tentative): Prof. Martin Riedmiller, Albert-Ludwigs University Freiburg, Germany

Learning is one of the most important capabilities of living systems, and processes involved in inference and learning are ingrained in many levels of organisation scale, e.g., from single neurons to organisations or societies. Much of the information processing involved in these processes is consequently distributed, and relies on local interactions among individual entities. On the other hand, many successful approaches from machine learning require some centralised processing, while in living systems no such requirement exists.

In this special session, we are looking for contributions that will address issues that involve information processing, inference, and learning, with a perspective on their application to Alife scenarios. These include for example methods to help characterising relevant information, self-organised encoding of information, decentralised approaches to learning, and inference mechanisms. Possible topics include, but are not limited to,

• information theoretic methods for analysing/describing Alife scenarios
• interactions between genetic evolution, and individual learning
• self-organised information processing
• intrinsically motivated learning
• guided self-organisation

To submit papers to this special session, please use the ACAL 2011 submission system and use Information Processing, Inference and / or Learning as a keyword.

=============================================================

ACAL11 — The Fifth Australian Conference on Artificial Life

6-8 December 2011, Perth, Western Australia

http://robots.newcastle.edu.au/ACAL11/

=============================================================

IMPORTANT DATES

Full Paper Submission: 28 June 2011

Acceptance/Rejection Notification: 15 August 2011

Camera Ready Submission: 10 September 2011

=============================================================

PAPER SUBMISSION AND AUTHOR INFORMATION

The ACAL11 proceedings will be published by Springer-Verlag in the “Lecture Notes in Artificial Intelligence (LNCS/LNAI/LNBI)” Series. Prospective authors are invited to submit their papers in English with no more than 12 pages in Springer LNAI style including results, figures and references. All papers for ACAL11 must be submitted electronically through the easychair conference management system:

http://www.easychair.org/conferences/?conf=acal11

All correctly submitted papers will be peer reviewed by at least three members of the international programme committee.

Paper templates in LNCS/LNAI format are available at Springer-Verlag’s website

http://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0

=============================================================

The symposium will take place at the CSIRO Campus in Sydney (Marsfield), Australia.

The exponentially increasing demand for computing power as well as physical and economic limitations has contributed to a proliferation of distributed and parallel computer architectures. To make better use of current and future high-performance computing, and to fully benefit from these massive amounts of data, we must discover, understand and exploit the available parallelism in machine learning. Simultaneously, we have to model data in an adequate manner while keeping the models as simple as possible, by making use of a sparse representation of the data or sparse modelling of the respective underlying problem.

The invited speakers are:

Samy Bengio (Google Research, CA, USA)
Barbara Hammer (University of Bielefeld, Germany)
Yann LeCun (New York University, NY, USA)
Michael Mahoney (Stanford University, CA, USA)

Call for Papers / Extended Abstracts

Through a combination of invited talks, contributed presentations, discussions and posters, we hope to gain a better understanding of available algorithms and best practices, as well as their inherent limitations.
We are looking for submissions of short papers / extended abstracts (at most 4 pages in NIPS format), in one or more of the following areas:

- Distributed, Multicore and Cluster based Learning Techniques
- Machine Learning on Alternative Hardware (GPUs, Robots, Sensor Networks, Mobile Phones, Cell Processors …)
- Sparsity in Machine Learning and Statistics
- Learning results and techniques on Massive Datasets
- Dimensionality Reduction, Sparse Matrix, Large Scale Kernel Methods
- Fast Online Algorithms for Large Scale Data
- Parallel Computing Tools and Libraries

Selected submissions will be considered for a special issue of a journal or a collected volume on the topic of the symposium. A separate call for papers will then be issued after the event for the special issue/collected volume. Please refer to the web page for further details.

Attendance to DMMD 2011 is free, but limited to approx. 50 participants (first in, best dressed – please register by email).

We can not provide travel support, but for a limited (small) number of interstate/overseas students, we will organise free accommodation. Priority will be given to students with an accepted paper. If you would like to be considered for this, please send an email to apply (deadline 1 November 2010).

Important Dates
Submission deadline: 1 November, 2010
Registration deadline: 31 December, 2010
Symposium: 18-20 January, 2011

Program Committee

Samy Bengio (Google Research, CA, USA)
Joschka Boedecker (Osaka University, Japan)
Stephan Chalup (University of Newcastle, Newcastle)
Tim Cornwell (CSIRO CASS, Sydney)
Ying Guo (CSIRO ICT Centre, Sydney)
Barbara Hammer (University of Bielefeld, Germany)
Yann LeCun (New York University, NY, USA)
Simon Lucey (CSIRO ICT Centre, Sydney)
Michael Mahoney (Stanford University, CA, USA)
N. Michael Mayer (National Chung Cheng University, Taiwan)
Mikhail Prokopenko (CSIRO ICT Centre, Sydney)
Scott Sanner (NICTA & ANU, Canberra)
John A. Taylor (CSIRO CMIS, Canberra)
Rosalind Wang (CSIRO ICT Centre, Sydney)

In this paper, we present an approach to improve the hidden layer of recurrent neural networks, guided by the learning goal of the system, and apply this new method to reservoir computing approaches. Reservoir computing uses, in general, a fixed, randomly initialised hidden layer. A consequence of this is that performance is usually quite good, but not necessarily optimal for the task at hand. There exist self-organised approaches – like intrinsic plasticity – that are able to improve performance of reservoir computing approaches, but usually, they just consider the input to the system, and don’t take the actual task of the system into account.

Our reservoir adaptation optimises the information transfer at each individual unit, dependent on properties of the information transfer between input and (desired) output of the system. Using synthetic data, we show that this reservoir adaptation improves the performance of offline echo state learning and Recursive Least Squares Online Learning.

ICONIP 2010 takes place from the 22nd–25th November 2010 in Sydney, Australia.

The workshop is comprised of a group of researchers with diverse yet related interests, overlapping in the area of self-organizing systems and methods for characterizing those systems in ways that may ultimately allow them to be guided toward prespecified goals. Information theory and graph theory are core to many of these methods; quantifying complexity and its sources a common theme.

If interested in participating, send an extended abstract to the email addresses on the workshop web site.  Selected works from the workshop will likely be published in a special journal issue (as has been the case in the past).  More information on the GSO-2010 web site.

guided self-organisation, workshop, artificial life, ai

The name “cyber-physical system” (CPS) was chosen by the NSF and other United States federal agencies for systems that coherently combine computational and physical elements.

The CPS field builds up on knowledge and practical experiences of embedded systems, sensor networks, multi-robot teams, modular/swarm robotics, amorphous computing, programmable materials, evolvable/adaptive hardware, etc., and yet promise to form a unique field.

This Workshop will focus on distributed computation in CPS – the computation processes that integrate multiple data streams, compress and structure high-dimensional information, synchronise the distributed dynamics, adapt to topological changes within networks, optimise multiple sensorimotor loops, etc.

Several prominent invited speakers from Australia, Spain and USA will present different aspects of this rapidly developing research field.

Anyone interested in participating in the workshop is encouraged to submit a two-page extended abstract by May 16, 2010. Notifications will be sent by June 11, 2010 to all those who will be invited to the workshop. All accepted submissions will be allocated an oral presentation slot. See the Workshop Web Page for details.

cyber-physical systems, workshop, australia, call for papers, Sydney, australasia, sensor networks

Topics at NIPS 2009 are (click on the images for a larger version):

Below is another version, this time by using the titles and abstracts as published in the program (pruned by some frequently occurring words such as University or the days of the week). Likewise created using http://www.wordle.net/.

NIPS 2009 Topics word cloud

nips, nips 2009, neural information processing systems, topics, conference

Reservoir computing (RC) is a recent paradigm in the field of recurrent neural networks. Networks in RC have a sparsely and randomly connected fixed hidden layer, and only output connections are trained. RC networks have recently received increased attention as a mathematical model for generic neural microcircuits to investigate and explain computations in neocortical columns. Applied to specific tasks, their fixed random connectivity, however, leads to significant variation in performance. Few problem-specific optimization procedures are known, which would be important for engineering applications, but also in order to understand how networks in biology are shaped to be optimally adapted to requirements of their environment. We study a general network initialization method using permutation matrices and derive a new unsupervised learning rule based on intrinsic plasticity (IP). The IP-based learning uses only local learning, and its aim is to improve network performance in a self-organized way. Using three different benchmarks, we show that networks with permutation matrices for the reservoir connectivity have much more persistent memory than the other methods but are also able to perform highly nonlinear mappings. We also show that IP-based on sigmoid transfer functions is limited concerning the output distributions that can be achieved.

neurophysiology, optimisation, physiological models, recurrent neural nets, unsupervised learning, reservoir computing, echo state networks