Self-Organization of Spatio-Temporal Hierarchy via Learning of Dynamic Visual Image Patterns on Action Sequences

• Published in: PloS one 2015-07, Vol.10 (7), p.e0131214-e0131214
• Main Authors: Jung, Minju, Hwang, Jungsik, Tani, Jun
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Biological computing; Brain; Computation; Computational neuroscience; Computer engineering; Computer science; Cortex (temporal); Electrical engineering; Experiments; Human motion; Humans; Information processing; Learning; Mathematical models; Motor task performance; Neural networks; Neurosciences; Object recognition; Pattern recognition; Spatial data; Structural hierarchy; Temporal lobe; Vision systems; Visual cortex; Visual Cortex - physiology; Visual discrimination learning
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0131214

It is well known that the visual cortex efficiently processes high-dimensional spatial information by using a hierarchical structure. Recently, computational models that were inspired by the spatial hierarchy of the visual cortex have shown remarkable performance in image recognition. Up to now, however, most biological and computational modeling studies have mainly focused on the spatial domain and do not discuss temporal domain processing of the visual cortex. Several studies on the visual cortex and other brain areas associated with motor control support that the brain also uses its hierarchical structure as a processing mechanism for temporal information. Based on the success of previous computational models using spatial hierarchy and temporal hierarchy observed in the brain, the current report introduces a novel neural network model for the recognition of dynamic visual image patterns based solely on the learning of exemplars. This model is characterized by the application of both spatial and temporal constraints on local neural activities, resulting in the self-organization of a spatio-temporal hierarchy necessary for the recognition of complex dynamic visual image patterns. The evaluation with the Weizmann dataset in recognition of a set of prototypical human movement patterns showed that the proposed model is significantly robust in recognizing dynamically occluded visual patterns compared to other baseline models. Furthermore, an evaluation test for the recognition of concatenated sequences of those prototypical movement patterns indicated that the model is endowed with a remarkable capability for the contextual recognition of long-range dynamic visual image patterns.