About
3
Publications
210
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
0
Citations
Citations since 2017
Publications
Publications (3)
We have previously shown that during top-down attentional modulation (stimulus expectation) correlations of the beta signals across the primary visual cortex were uniform, while during bottom-up attentional processing (visual stimulation) their values were heterogeneous. These different patterns of attentional beta modulation may be caused by feed-...
Lateral inhibition is known to occur at all levels of processing of visual information: from retinal ganglion cells, through principal cells in LGN to primary cortical areas [1]. The role of this connectivity module is to contrast lateral variation within the simultaneously processed upstream information.
Our work is based on local field potential...
Network
Projects
Project (1)
Deep Convolutional Neural Network (CNN) or ConvNet is becoming the mainstream in scientific community. Recent studies show that deep neural network develops representations that challenge to mimic mammalian neocortex. Despite their superior object categorization abilities, ConvNets show rather poor object localization results; with the top-performing model (GoogLeNet).In this study new biological motivated deep learning architecture is proposed. New architecture consists of model of Visual Attention and Tensor Decomposition based on the Radix (2x2) Hierarchical Singular Value Decomposition. Proposed tensor decomposition simulates 2x2 receptive fields. The proposed architecture significantly improves the CNN performance for real time object localization and recognition.
