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

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

Original papers are solicited in all areas of unconventional computation; typical, but not exclusive, topics are: natural computing including quantum, cellular, molecular, neural, and membrane computing as well as evolutionary paradigms; chaos and dynamical systems based computing; proposals for computations going beyond the Turing model.

Submissions are due on April 14th, 2008. The call for papers and the conference poster are available from the conference homepage.

Technorati Tags: unconventional, evolutionary computing, conference, quantum computing, chaos, cfp, neural computing, dynamical systems

Architectures for teams of robots, Ambient Intelligence, Biologically inspired systems, Control issues in multi-robot systems, Distributed decision making/problem solving, Distributed/cooperative perception, Distributed planning, Distributed task execution, Human and robot interaction, Learning and adaptation in teams of robots, Multi-robot applications in exploration, search and rescue, Mobiligence (Emergence of Intelligence through Mobility), Modular robotics, Network robotics, Performance metrics for robot teams, Reconfigurable robots, Robot societies, Self-organizing robotic systems, Sensor networks, Swarm robotics, Task allocation.

The conference takes place in Tsukuba, Ibaraki, Japan, Nov. 17-19, 2008. Full paper submission is June 30, 2008. For details, check out the web page.

Technorati Tags: CFP, conference, robotics, distributed systems, autonomous robots