dc.contributor.author Gao, Yuguang dc.date.accessioned 2019-10-15T16:49:21Z dc.date.available 2021-08-29T06:00:18Z dc.date.issued 2019-08-30 dc.identifier.other Gao_cornellgrad_0058F_11340 dc.identifier.other http://dissertations.umi.com/cornellgrad:11340 dc.identifier.other bibid: 11050641 dc.identifier.uri https://hdl.handle.net/1813/67657 dc.description.abstract This thesis discusses a few interesting topics regarding fundamental aspects of learning in the following prevalent application scenarios: (1) training a neural network for image classification, and (2) using a channel code for universal communication at capacity. For the classification problem, we aim to develop a better understanding of what representations each layer of the network learns. In particular, we compare the higher-layer activations of two neural networks with identical architecture but different initializations via adaptive $k$NN graph approximation of the underlying manifold, and we show that there are vast similarities between the underlying manifolds of the two networks but with discrepancy in potentially highly-curved regions. We also investigate locality of the receptive field in the Convolutional Neural Networks by using semi-localized filters with random neuron connection, where we find out that the receptive field might be beyond local for feature extraction as is hard coded in traditional design. For the communication problem, we study universal channel coding under the high-dimensional statistical setting beyond Shannon's classical framework, and we prove a series of theorems that may surprisingly indicate a need to learn the entire channel in order to achieve its capacity. dc.language.iso en_US dc.subject Electrical engineering dc.title On Some Fundamental Aspects of Learning in Artificial Neural Networks and Universal Channel Codes dc.type dissertation or thesis thesis.degree.discipline Electrical and Computer Engineering thesis.degree.grantor Cornell University thesis.degree.level Doctor of Philosophy thesis.degree.name Ph.D., Electrical and Computer Engineering dc.contributor.chair Hopcroft, John E. dc.contributor.committeeMember Tong, Lang dc.contributor.committeeMember Kleinberg, Robert David dcterms.license https://hdl.handle.net/1813/59810 dc.identifier.doi https://doi.org/10.7298/6a79-d633
﻿