2026-09-23T05:47:21Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/116250 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Viswanath, Pramod Viswanath, Pramod Hajek, Bruce Rayadurgam, Srikant Sun, Ruoyu Oh, Sewoong 2022-08 application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-15 without embargo terms The student, Ashok Makkuva, accepted the attached license on 2022-07-15 at 00:05. The student, Ashok Makkuva, submitted this Dissertation for approval on 2022-07-15 at 00:10. This Dissertation was approved for publication on 2022-07-15 at 12:22. DSpace SAF Submission Ingestion Package generated from Vireo submission #18327 on 2022-11-15 at 18:21:15 Deep code: representation and learning algorithms for neural networks & their applications to communication codes Makkuva, Ashok Vardhan 2022-07-15 machine-learning LSTM GRU mixture-of-experts deep learning KO codes channel codes error-correcting-codes Reed-Muller codes Polar codes Codes are the backbone of modern information age. Codes, composed of encoder and decoder pairs, are the basic mathematical objects that enable reliable communication. Landmark codes include convolutional, Reed-Muller, turbo, LDPC, and polar: each is linear and represents a mathematical breakthrough. Their impact on humanity is huge; each of these codes has been used in global communication standards over the past six decades. On the other hand, designing codes is a challenging task, mostly driven by human ingenuity. Befittingly, historically, the progress in discovery of codes has been sporadic. In this thesis, we present a new paradigm to invent codes via harnessing tools from deep-learning. Our major result is the invention of \emph{KO codes}, a computationally efficient family of deep-learning driven codes that outperform the state-of-the-art RM and polar codes, in the challenging short-to-medium block length regime. The key technical innovation behind KO codes is the design of a novel family of neural architectures inspired by the computation tree of the {\bf K}ronecker {\bf O}peration (KO) central to RM and polar codes. These architectures pave the way for discovery of a much richer class of hitherto unexplored non-linear codes. This design technique can be viewed as an instantiation of the classical neural augmentation principle. In the process, we also study a popular neural network model called Mixture-of-Experts (MoE) that realizes this principle. We provide the first set of consistent and efficient algorithms with global learning guarantees for learning the parameters in a MoE which has been an open problem for more than two decades. Thesis eng https://hdl.handle.net/2142/116250 Copyright 2022 Ashok Makkuva Ph.D. Dissertation Electrical & Computer Engr University of Illinois at Urbana-Champaign Electrical & Computer Eng