Investigation into Sub-Receptive Fields of Retinal Ganglion Cells with Natural Images

Vance, J. Philip; Das, Proloy; Coleman, A. Sonya; Kerr, Dermot; Kerr, P; McGinnity, Martin

doi:10.1109/ijcnn.2018.8489324

Cited by 1 publication

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Information present in grayscale images can be represented in many different ways. In this study the mean contrast of each SRF contained within the RF is [9,11]. The mean contrast is defined as…”

Section: Assessing Input-output Relationshipmentioning

confidence: 99%

“…Inspired by previous modelling approaches for natural image processing [11][12][13] a number of different machine learning techniques are considered in this study; namely a Multi-Layer Perceptron (MLP) [14], Bayesian Regularised Neural Networks (BRNN) [15], Support Vector Regression (SVR) [16] and k-Nearest Neighbours (k-NN) [17]. Methodological details of each model can be found in the associated literature [18].…”

Section: Modelling Retinal Behaviourmentioning

confidence: 99%

See 1 more Smart Citation

Computational Approach to Identifying Contrast-Driven Retinal Ganglion Cells

Gault

Vance

McGinnity

et al. 2021

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

The retina acts as the primary stage for the encoding of visual stimuli in the central nervous system. It is comprised of numerous functionally distinct cells tuned to particular types of visual stimuli. This work presents an analytical approach to identifying contrast-driven retinal cells. Machine learning approaches as well as traditional regression models are used to represent the input-output behaviour of retinal ganglion cells. The findings of this work demonstrate that it is possible to separate the cells based on how they respond to changes in mean contrast upon presentation of single images. The separation allows us to identify retinal ganglion cells that are likely to have good model performance in a computationally inexpensive way.

show abstract

Section: Assessing Input-output Relationshipmentioning

confidence: 99%

Section: Modelling Retinal Behaviourmentioning

confidence: 99%