Next Article in Journal
Neural Stem Cells/Neuronal Precursor Cells and Postmitotic Neuroblasts in Constitutive Neurogenesis and After ,Traumatic Injury to the Mesencephalic Tegmentum of Juvenile Chum Salmon, Oncorhynchus keta
Previous Article in Journal
Cerebellar Transcranial Magnetic Stimulation Reduces the Silent Period on Hand Muscle Electromyography During Force Control
Previous Article in Special Issue
The Effect of Aging on the ERP Correlates of Feedback Processing in the Probabilistic Selection Task
Open AccessArticle

CINET: A Brain-Inspired Deep Learning Context-Integrating Neural Network Model for Resolving Ambiguous Stimuli

1
Department of Electrical & Computer Engineering, Southern Illinois University, Carbondale, IL 62901, USA
2
Vanderbilt Brain Institute, Vanderbilt University, Nashville, TN 37232, USA
*
Author to whom correspondence should be addressed.
Brain Sci. 2020, 10(2), 64; https://doi.org/10.3390/brainsci10020064
Received: 10 December 2019 / Revised: 17 January 2020 / Accepted: 22 January 2020 / Published: 24 January 2020
(This article belongs to the Collection Collection on Cognitive Neuroscience)
The brain uses contextual information to uniquely resolve the interpretation of ambiguous stimuli. This paper introduces a deep learning neural network classification model that emulates this ability by integrating weighted bidirectional context into the classification process. The model, referred to as the CINET, is implemented using a convolution neural network (CNN), which is shown to be ideal for combining target and context stimuli and for extracting coupled target-context features. The CINET parameters can be manipulated to simulate congruent and incongruent context environments and to manipulate target-context stimuli relationships. The formulation of the CINET is quite general; consequently, it is not restricted to stimuli in any particular sensory modality nor to the dimensionality of the stimuli. A broad range of experiments is designed to demonstrate the effectiveness of the CINET in resolving ambiguous visual stimuli and in improving the classification of non-ambiguous visual stimuli in various contextual environments. The fact that the performance improves through the inclusion of context can be exploited to design robust brain-inspired machine learning algorithms. It is interesting to note that the CINET is a classification model that is inspired by a combination of brain’s ability to integrate contextual information and the CNN, which is inspired by the hierarchical processing of information in the visual cortex.
Keywords: Context effect; deep learning; convolution neural networks; ambiguous stimuli Context effect; deep learning; convolution neural networks; ambiguous stimuli
MDPI and ACS Style

Amerineni, R.; Gupta, R.S.; Gupta, L. CINET: A Brain-Inspired Deep Learning Context-Integrating Neural Network Model for Resolving Ambiguous Stimuli. Brain Sci. 2020, 10, 64.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop