Abstract
Dynamic neural fields (DNFs) are dynamical systems models that approximate the activity of large, homogeneous, and recurrently connected neural networks based on a mean field approach. Within dynamic field theory, the DNFs have been used as building blocks in architectures to model sensorimotor embedding of cognitive processes. Typically, the parameters of a DNF in an architecture are manually tuned in order to achieve a specific dynamic behavior (e.g., decision making, selection, or working memory) for a given input pattern. This manual parameters search requires expert knowledge and time to find and verify a suited set of parameters. The DNF parametrization may be particular challenging if the input distribution is not known in advance, e.g., when processing sensory information. In this paper, we propose the autonomous adaptation of the DNF resting level and gain by a learning mechanism of intrinsic plasticity (IP). To enable this adaptation, an input and output measure for the DNF are introduced, together with a hyper parameter to define the desired output distribution. The online adaptation by IP gives the possibility to pre-define the DNF output statistics without knowledge of the input distribution and thus, also to compensate for changes in it. The capabilities and limitations of this approach are evaluated in a number of experiments.
Highlights
A Dynamic Neural Field is a description of activity of a large homogeneous neuronal population (Wilson and Cowan, 1973; Amari, 1977; Coombes et al, 2014; Schöner and Spencer, 2015)
For evaluating the Dynamic neural fields (DNFs) with intrinsic plasticity (IP), an input time series is constructed from haptic recordings of robotic object manipulations done in Strub et al (2014a)
As the object manipulations are done with two fingers, there may be none, one, or two simultaneous contacts at every point in time
Summary
A Dynamic Neural Field is a description of activity of a large homogeneous neuronal population (Wilson and Cowan, 1973; Amari, 1977; Coombes et al, 2014; Schöner and Spencer, 2015). The DNF equation is obtained as a mean-field approximation of the dynamics of a network of spiking neurons and describes the dynamics of a continuous activation function, spanned over a feature dimension, such as color, location, velocity, or other perceptual or motor parameters, to which the neurons in the underlying population respond. The sigmoidal non-linearity determines the output of the DNF. The recurrent connectivity pattern and sigmoid output function of the DNF lead to non-linear properties of this model. These properties enabled its successful application in modeling cognitive functions in humans: e.g., formation of a representation, working memory, decision making, rule learning, or executive control (Schöner and Spencer, 2015), as well as for control of cognitive robots (Bicho et al, 2011; Sandamirskaya et al, 2013)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
