Browse by author
Lookup NU author(s): Scott Stainton,
Professor Satnam Dlay
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
© 2018 IEEE. Deep learning is a sub-field of machine learning with their models being vaguely inspired by the communication patterns and information processing of a nervous system. In a deep learning model each layer of the network, which is build up of multiple neurons, transforms its input data into slightly more abstract and composite abstractions. Within a convolutional neural network (CNN), the first layer of neurons may be transform its raw input pixels to encoded edges, with the next layer encoding arrangements of edges, with the next layer more abstract features such as eyes and noses. However, locating which exact neurons in each layer are looking for each abstract feature is still a hot area for research. Here we show a novel way to pinpoint each neuron in the hidden layers that is searching for a specific feature that is believed to play a pivotal role in the classification task. We found that by removing the feature of interest from the original image and running this through the CNN, each neurons activation map can be compared to the activation generated by the original image using t-SNE. This allowed us to successfully located the individual neurons in the network that are significantly effected by the removal of this feature and hence changing the classification. This method allows us to get a better understanding of what the network has learnt and how important this learnt information is when coming to the final classification.
Author(s): Barney S, Stainton S, Catt M, Dlay S
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: 2018 11th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2018
Year of Conference: 2018
Online publication date: 27/09/2018
Acceptance date: 18/07/2018
Publisher: Institute of Electrical and Electronics Engineers Inc.
Library holdings: Search Newcastle University Library for this item