Abstract
We discuss a recently proposed approach to solve the classic feature-binding problem in primate vision that uses neural dynamics known to be present within the visual cortex. Broadly, the feature-binding problem in the visual context concerns not only how a hierarchy of features such as edges and objects within a scene are represented, but also the hierarchical relationships between these features at every spatial scale across the visual field. This is necessary for the visual brain to be able to make sense of its visuospatial world. Solving this problem is an important step towards the development of artificial general intelligence. In neural network simulation studies, it has been found that neurons encoding the binding relations between visual features, known as binding neurons, emerge during visual training when key properties of the visual cortex are incorporated into the models. These biological network properties include (i) bottom-up, lateral and top-down synaptic connections, (ii) spiking neuronal dynamics, (iii) spike timing-dependent plasticity, and (iv) a random distribution of axonal transmission delays (of the order of several milliseconds) in the propagation of spikes between neurons. After training the network on a set of visual stimuli, modelling studies have reported observing the gradual emergence of polychronization through successive layers of the network, in which subpopulations of neurons have learned to emit their spikes in regularly repeating spatio-temporal patterns in response to specific visual stimuli. Such a subpopulation of neurons is known as a polychronous neuronal group (PNG). Some neurons embedded within these PNGs receive convergent inputs from neurons representing lower- and higher-level visual features, and thus appear to encode the hierarchical binding relationship between features. Neural activity with this kind of spatio-temporal structure robustly emerges in the higher network layers even when neurons in the input layer represent visual stimuli with spike timings that are randomized according to a Poisson distribution. The resulting hierarchical representation of visual scenes in such models, including the representation of hierarchical binding relations between lower- and higher-level visual features, is consistent with the hierarchical phenomenology or subjective experience of primate vision and is distinct from approaches interested in segmenting a visual scene into a finite set of objects.
Highlights
The feature-binding problem concerns how the visual system represents the hierarchical relationships between features
In contrast to the results shown in figure 12a, when analysing the stimulus information carried by the spike-pair polychronous neuronal group (PNG), the best performance is achieved by the full network architecture incorporating FF þ FB þ LAT connections, which is closest to the actual architecture of the visual cortex
Eguchi et al [9] demonstrated that embedded within the stimulus-specific PNGs that emerged in the full network architecture during training on the circle, heart and star shown in figure 11 were binding neurons of the kind illustrated in figures 3a and 4a
Summary
The feature-binding problem concerns how the visual system represents the hierarchical relationships between features (such as edges and objects). The simulation studies carried out by these authors reported the emergence of stimulus-specific spatio-temporal patterns of spikes (PNGs) within the higher network layers, which are repeated across different presentations of the same stimulus, even when the spike timings of the stimulus representations in the input layer were randomized. These authors investigated the emergence of both large-scale PNGs consisting of many 4 neurons, as well as spike-pair PNGs consisting of just two neurons that carried high levels of stimulus-specific information.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.