Skip navigation
Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp011c18dj96t
Title: Holistically Interpreting Deep Neural Networks via Channel Ablation
Authors: Dhopte, Vedant
Advisors: Fong, Ruth
Department: Computer Science
Class Year: 2022
Abstract: This paper aims to contribute to the field of convolutional neural network interpretability by analyzing the most significant channels within layers of AlexNet used in making image classifications. We perform various ablation (or "zero-ing out") methods on the layers of AlexNet for a wide variety of images to determine the crucial set of neurons needed to make a correct prediction. We introduce multiple ablation methodologies called top-down and bottom-up ablation that aim to delete the most and least activated channels in a particular model layer. We find that most layers, especially those later in the model, allow for a large amount of ablation of the least significant channels. This points to the fact that object recognition may be specialized to a subset of significant neurons. We also find that ablating this set of crucial neurons has great impact on the model’s prediction for an image, further solidifying the confidence that these channels are indeed highly class specific. In summary, we aim to add to the general knowledge of how the inner-workings of convolutional neural networks function for a particular object recognition task.
URI: http://arks.princeton.edu/ark:/88435/dsp011c18dj96t
Type of Material: Princeton University Senior Theses
Language: en
Appears in Collections:Computer Science, 1987-2024

Files in This Item:
File Description SizeFormat 
DHOPTE-VEDANT-THESIS.pdf4.99 MBAdobe PDF    Request a copy


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