Show Reference: "Adaptive training of cortical feature maps for a robot sensorimotor controller"

Adaptive training of cortical feature maps for a robot sensorimotor controller Neural Networks, Vol. 44 (August 2013), pp. 6-21, doi:10.1016/j.neunet.2013.03.004 by Samantha V. Adams, Thomas Wennekers, Sue Denham, Phil F. Culverhouse
@article{adams-et-al-2013,
    abstract = {This work investigates self-organising cortical feature maps ({SOFMs}) based upon the Kohonen {Self-Organising} Map ({SOM}) but implemented with spiking neural networks. In future work, the feature maps are intended as the basis for a sensorimotor controller for an autonomous humanoid robot. Traditional {SOM} methods require some modifications to be useful for autonomous robotic applications. Ideally the map training process should be self-regulating and not require predefined training files or the usual {SOM} parameter reduction schedules. It would also be desirable if the organised map had some flexibility to accommodate new information whilst preserving previous learnt patterns. Here methods are described which have been used to develop a cortical motor map training system which goes some way towards addressing these issues. The work is presented under the general term 'Adaptive Plasticity' and the main contribution is the development of a 'plasticity resource' ({PR}) which is modelled as a global parameter which expresses the rate of map development and is related directly to learning on the afferent (input) connections. The {PR} is used to control map training in place of a traditional learning rate parameter. In conjunction with the {PR}, random generation of inputs from a set of exemplar patterns is used rather than predefined datasets and enables maps to be trained without deciding in advance how much data is required. An added benefit of the {PR} is that, unlike a traditional learning rate, it can increase as well as decrease in response to the demands of the input and so allows the map to accommodate new information when the inputs are changed during training.},
    author = {Adams, Samantha V. and Wennekers, Thomas and Denham, Sue and Culverhouse, Phil F.},
    doi = {10.1016/j.neunet.2013.03.004},
    issn = {08936080},
    journal = {Neural Networks},
    keywords = {ann, cortex, neurorobotics, robot},
    month = aug,
    pages = {6--21},
    posted-at = {2013-10-08 09:26:01},
    priority = {2},
    title = {Adaptive training of cortical feature maps for a robot sensorimotor controller},
    url = {http://dx.doi.org/10.1016/j.neunet.2013.03.004},
    volume = {44},
    year = {2013}
}

See the CiteULike entry for more info, PDF links, BibTex etc.

Adams et al. use SOM-like algorithms to model biological sensori-motor control and develop robotic sensori-motor controllers.

Adams et al. state that others have used SOM-like algorithms for modelling biology and for robotic applications, before (and list examples).

Adams et al. argue that, since the brain is fast and requires little energy, researching biomimetic solutions can help solve the problems that robots have limited energy resources and computing power.

Although Adams et al. argue that biomimetic approaches to robotics promise less energy consumption and processing requirements, they implicitly acknowledge that using spiking neural networks will increase these requirements and is only feasible, if at all, because of recent developments in software and hardware.

A SOM that is to learn continuously cannot continuously decrease neighborhood interaction width and learning rate.

It is helpful if these parameters are self-regulated, like in PSOM.

Adams et al. present a Spiking Neural Network implementation of a SOM which uses

  • spike-time dependent plasticity
  • a method to adapt the learning rate
  • constant neighborhood interaction width

Adams et al. note that there have been a number of attempts at spiking SOM implementations (and list a few).