oliver.obst.eu » learning

The First Australasian Workshop on Computation in Cyber-Physical Systems

oliver — Thu, 25 Mar 2010 23:19:06 +0000

You are invited to submit to and/or attend The First Australasian Workshop on Computation in Cyber-Physical Systems (CompCPS-2010).
We are organising this event here in Sydney, on the 15-16 July, in the Lecture Theatre at the CSIRO Marsfield site.

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

What is going on at NIPS 2009?

oliver — Tue, 08 Dec 2009 07:23:02 +0000

To get a quick overview on what is happening this year at NIPS, I have taken the titles of accepted papers and used the resulting text to produce a word cloud (a screen shot created using http://www.wordle.net/). The word cloud shows the hottest topics as the largest words (unsurprisingly, ‘learning’ is the most prominent word in all the titles). But see for yourselves…

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

Studies on Reservoir Initialization and Dynamics Shaping in Echo State Networks

oliver — Thu, 19 Feb 2009 12:49:54 +0000

In a paper that was recently accepted at the European Symposium on Artificial Neural Networks (ESANN 2009), we look at different ways to influence the performance of echo state networks. Traditionally, echo state networks and other reservoir computing approaches use a fixed random connected reservoir, which leads to significant variation in performance. Only few problem specific optimisation procedures are known to date. We study a general initialization method using permutation matrices and derive a new unsupervised learning rule based on intrinsic plasticity (IP) for echo state networks. Using three different benchmarks, we show that networks with permutation matrices for the reservoir connectivity have much longer memory than the other methods, but are also able to perform highly non-linear mappings. We also show that IP based on sigmoid transfer functions is limited concerning the output distributions that can be achieved.

Studies on Reservoir Initialization and Dynamics Shaping in Echo State Networks,
J. Boedecker, O. Obst, N.M. Mayer, M. Asada. The full paper will be available after the conference (April) is now available.

neural networks, intrinsic plasticity, echo state networks, reservoir computing

CFP: ICDL 2009, 8-th IEEE International Conference on Development and Learning

oliver — Wed, 03 Dec 2008 20:56:18 +0000

ICDL is a multidisciplinary conference pertaining to all subjects related to
the development and learning processes of natural and artificial systems,
including perceptual, cognitive, behavioral, emotional and all other mental
capabilities that are exhibited by humans, higher animals, and robots. Its
visionary goal is to understand autonomous development in humans and higher
animals in biological, functional, and computational terms, and to enable such
development in artificial systems. ICDL strives to bring together researchers
in neuroscience, psychology, artificial intelligence, robotics and other
related areas to encourage understanding and cross-fertilization of latest
ideas. ICDL2009 is held in Shanghai, June 5-7, 2009.
For a list of topics of see the CfP at http://www.icdl09.org/.

icdl, conference, cfp, learning, development, robotics

Summer schools on Neural Networks and on Functional Genomics

oliver — Mon, 12 May 2008 03:36:36 +0000

There is an international summer school on Functional Genomics at the Baia Samuele Conference Centre, Scicli, Sicily, Italy, July 5th-19th 2008. The webpage is http://www.functional-genomics.it/school, registration deadline May 20th.

Also in Italy, there is the Bertinoro International Summer School of Natural Computation – BNC 2008. It is to be held at the University Residential Center – Bertinoro (Forlì-Cesena), Italy, September 20-27, 2008. See the webpage at http://www.dmi.unict.it/~bnc/index.html for details.

Finally, in Porto, there is NN2008, the 2008 summer school on neural networks in classification, regression and data mining. July 7-11, Porto, Portugal. http://www.nn.isep.ipp.pt.

Technorati Tags: summer school, italy, portugal, neural networks, genomics, call for participation

CFP: Special Issue on Perspectives and Challenges for Recurrent Neural Networks

oliver — Mon, 12 May 2008 00:32:37 +0000

Special issue of the Elsevier Journal of Algorithms in Cognition, Informatics and Logic.

Submissions connected to the following non-exhaustive list of topics are particularly encouraged:

new learning paradigms of RNNs such as unsupervised learning or reservoire learning
biologically plausible methods
integration of RNNs and symbolic reasoning
universal approaches for general data structures such as sets or graphs
methods which address the generalization ability of RNNs
challenging applications which have the potential to be benchmark problems
visionary papers concerning the future of RNNs

Deadline for submissions is 18th of July, 2008.

Technorati Tags: neural networks, rnn, journal, cfp, special issue, recurrent neural networks

CFP: Inaugural Issue for International Journal of Social Robotics

oliver — Tue, 22 Apr 2008 18:50:47 +0000

There is a new international Springer journal on social robotics, covering quite a range of topics in this field. Authors are invited to submit scientific, technological and philosophical advances in social robots, and their interactions and communications with humans, especially innovative ideas and concepts, new discoveries and improvements, as well as novel applications on the latest fundamental advances in the core technologies that form the backbone of Social Robotics, distinguished developmental projects, as well as seminal works in aesthetic design, ethics and philosophy, studies on social impact and influence pertaining to, and its interaction and communication with human beings and its social impact on our society.

The submission deadline is the 1st July, 2008. For details, check http://www.editorialmanager.com/soro/.

Technorati Tags: cfp, springer, journal, robotics

New Paper on Echo State Networks

oliver — Fri, 18 Apr 2008 08:16:28 +0000

At IPSN 2008, I’m going to present our work “Using Echo State Networks for Anomaly Detection in Underground Coal Mines”. In this work, we investigate the problem of identifying anomalies in monitoring critical gas concentrations using a sensor network in an underground coal mine. In this domain, one of the main problems is a provision of mine specific anomaly detection, with cyclical (moving) instead of flatline (static) alarm threshold levels. An additional practical difficulty in modelling a specific mine is the lack of fully labelled data of normal and abnormal situations. We present an approach addressing these difficulties based on echo state networks learning mine specific anomalies when only normal data is available. Echo state networks utilize incremental updates driven by new sensor readings, thus enabling a detection of anomalies at any time during the sensor network operation. We evaluate this approach against a benchmark — Bayes Network based anomaly detection, and observe that the quality of the overall predictions is comparable to the benchmark. However, the echo state networks maintain the same level of predictive accuracy for data from multiple sources. Therefore, the ability of echo state networks to model dynamical systems make this approach more suitable for anomaly detection and predictions in sensor networks. Check out the details here.

Technorati Tags: Sensor networks, Echo State Networks, Neural Networks, Anomaly detection, IPSN, 2008, Paper, Computer Science

CFP: Evolutionary and Self-Organizing Sensors, Actuators and Processing Hardware

oliver — Thu, 07 Feb 2008 06:11:23 +0000

There’s a special session at AHS-2008: the NASA/ESA Conference on Adaptive Hardware and Systems (June 22-25, 2008, Noordwijk, The Netherlands) on “Evolutionary and Self-Organizing Sensors, Actuators and Processing Hardware” (ESOSAPH). Recent technology has witnessed the advent of cheap ubiquitous sensing, processing and actuating capabilities for isolated, distributed or collective robotic systems. These appear in the form of intelligent materials, nano-motors and -sensors, Micro-Electro-Mechanical Systems (MEMS), grid processors, Avogadro-scale digital circuits and similar structures. Established conventional AI computation paradigms do not harness the full potential of this new type of technological ability that includes dynamic reconfiguration, addition or removal of sensors, actuators or processing hardware. Classical AI paradigms are inadequate to deal with the requirements of these scenarios which require flexible and adaptive acquisition, manipulation and distribution of information as opposed to sterile off-line AI software designs detached from concrete usage scenarios.

One is confronted with the necessity to adapt sensoric properties and/or configuration to a situation or task at hand, discovery of new sensoric modalities, the use of newly added actuators in novel ways, the necessity of reconfiguring computational hardware after being damaged, and much more. What all these requirements have in common is that, in general, there cannot be a full a priori appreciation of the possible scenarios that can occur during the lifetime of the involved hardware and software.

On the other hand, biological systems are capable to tackle such problems on a regular basis. E.g. the recovery of functionality in experiments where sensoric or neural tissues are transplanted to other than the original locations show that biological systems have a powerful potential to reconfigure their “hardware” and “software” to suit the relevant situation. Biologically inspired approaches, e.g. evolutionary and neural methods, as well as self-organization to tackle these challenges, have been increasingly found to be fruitful. Evolutionary sensorics, self-organizing and self-adaptive controllers, neural strategies have all provided new insights, methodologies, towards the achievement of self- and externally modified sensomotoric loops.

Solutions to these problems has an enormous potential and is amongst the most timely challenges: they would allow the construction of robust, cheap autonomous vehicles, sensor/actuator networks consisting of a large number of autonomous sensor/actuator units (’agents’) that interact with each other to obtain the best results. They would open the way to apply novel sensing/actuation materials for the construction of agents because the self-organized
adaptation mechanisms would be able to deal with the novelty.

The submission deadline is 28 Feb 2008. For details, check the web page

Technorati Tags: sensing, processing, actuation, workshop, cfp, NASA, Adaptive systems

Paper: Spatiotemporal Anomaly Detection in Gas Monitoring Sensor Networks

oliver — Thu, 31 Jan 2008 06:56:38 +0000

Our paper “Spatiotemporal Anomaly Detection in Gas Monitoring Sensor Networks” is currently being presented at the European conference on Wireless Sensor Networks (EWSN’08) in Bologna, Italy. In this paper, we use Bayesian Networks as a means for unsupervised learning and anomaly (event) detection in gas monitoring sensor networks for underground coal mines. We show that the Bayesian Network model can learn cyclical baselines for gas concentrations, and by this reduce false alarms usually caused by ﬂatline thresholds. You can check out the details here.

Technorati Tags: paper, sensor networks, bayesian networks, anomaly detection, coal mines