Implementation of Deep Feedforward Neural Network with CUDA backend for Efficient and Accurate Natural Image Classification

Examensarbete för masterexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/256344
Download file(s):
File Description SizeFormat 
256344.pdfFulltext1.88 MBAdobe PDFView/Open
Type: Examensarbete för masterexamen
Master Thesis
Title: Implementation of Deep Feedforward Neural Network with CUDA backend for Efficient and Accurate Natural Image Classification
Authors: von Hacht, August
Abstract: Recent advancements in techniques for constructing and training deep feedforward neural networks for classification tasks has enabled efficient training procedures leading to impressive results. This involves reducing overfitting due to over parameterized models, using an adaptive learning rate for avoiding exploding and vanishing gradients and symmetry breaking parameter initialization for efficient model optimization. Utilizing these techniques, this thesis concerns with the implementation of deep feedforward neural networks capable of efficient and accurate natural image classification. Four feedforward neural network models were constructed with the aim to classify tiny natural images from the CIFAR10 dataset. Having 3.274.634 trainable parameters for gray scale input and 4.259.274, 29.853.002 and 30.955.290 trainable parameters for rgb input, the training procedure utilizes a CUDA backend for efficient parameter optimization. The handwritten digits were classified with 97.31% accuracy and the tiny natural images were classified, using the best model, with 72.88% accuracy.
Keywords: Fysik;Physical Sciences
Issue Date: 2017
Publisher: Chalmers tekniska högskola / Institutionen för fysik (Chalmers)
Chalmers University of Technology / Department of Physics (Chalmers)
URI: https://hdl.handle.net/20.500.12380/256344
Collection:Examensarbeten för masterexamen // Master Theses



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.