• Login
• Admin

Turcsány, Diána (2016) Deep learning models of biological visual information processing. PhD thesis, University of Nottingham.

Preview

PDF (Thesis - as examined) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader Download (8MB) | Preview

Abstract

Improved computational models of biological vision can shed light on key processes contributing to the high accuracy of the human visual system. Deep learning models, which extract multiple layers of increasingly complex features from data, achieved recent breakthroughs on visual tasks. This thesis proposes such flexible data-driven models of biological vision and also shows how insights regarding biological visual processing can lead to advances within deep learning.

To harness the potential of deep learning for modelling the retina and early vision, this work introduces a new dataset and a task simulating an early visual processing function and evaluates deep belief networks (DBNs) and deep neural networks (DNNs) on this input. The models are shown to learn feature detectors similar to retinal ganglion and V1 simple cells and execute early vision tasks.

To model high-level visual information processing, this thesis proposes novel deep learning architectures and training methods. Biologically inspired Gaussian receptive field constraints are imposed on restricted Boltzmann machines (RBMs) to improve the fidelity of the data representation to encodings extracted by visual processing neurons. Moreover, concurrently with learning local features, the proposed local receptive field constrained RBMs (LRF-RBMs) automatically discover advantageous non-uniform feature detector placements from data.

Following the hierarchical organisation of the visual cortex, novel LRF-DBN and LRF-DNN models are constructed using LRF-RBMs with gradually increasing receptive field sizes to extract consecutive layers of features. On a challenging face dataset, unlike DBNs, LRF-DBNs learn a feature hierarchy exhibiting hierarchical part-based composition. Also, the proposed deep models outperform DBNs and DNNs on face completion and dimensionality reduction, thereby demonstrating the strength of methods inspired by biological visual processing.

Item Type:	Thesis (University of Nottingham only) (PhD)
Supervisors:	Bargiela, Andrzej Maul, Tomas Pridmore, Tony
Keywords:	deep learning, machine learning, visual information processing, biological vision, retinal modelling, neural computation, local receptive field constrained restricted Boltzmann machine, deep neural network, deep belief network, deep autoencoder, feature hub, self-adaptive structure, structure learning, face completion
Subjects:	Q Science > QA Mathematics > QA 75 Electronic computers. Computer science T Technology > TA Engineering (General). Civil engineering (General)
Faculties/Schools:	UK Campuses > Faculty of Science > School of Computer Science
Item ID:	35561
Depositing User:	Turcsány, Diána
Date Deposited:	13 Dec 2016 11:10
Last Modified:	13 Oct 2017 04:08
URI:	https://eprints.nottingham.ac.uk/id/eprint/35561

Actions (Archive Staff Only)

Edit View