eprintid: 19121
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/91/21
datestamp: 2024-06-04 14:11:34
lastmod: 2024-06-04 14:11:34
status_changed: 2024-06-04 14:04:55
type: conference_item
metadata_visibility: show
creators_name: Usmani, U.A.
creators_name: Usmani, M.U.
title: Theoretical Insights into Neural Networks and Deep Learning: Advancing Understanding, Interpretability, and Generalization
ispublished: pub
keywords: Deep learning; Learning algorithms; Learning systems, Activation functions; Convergence properties; Deep learning; Generalisation; Generalization capability; Interpretability; Learning models; Neural-networks; Theoretical analyse; Theoretical foundations, Network architecture
note: cited By 4; Conference of 2023 IEEE World Conference on Communication and Computing, WCONF 2023 ; Conference Date: 14 July 2023 Through 16 July 2023; Conference Code:192397
abstract: This work aims to provide profound insights into neural networks and deep learning, focusing on their functioning, interpretability, and generalization capabilities. It explores fundamental aspects such as network architectures, activation functions, and learning algorithms, analyzing their theoretical foundations. The paper delves into the theoretical analysis of deep learning models, investigating their representational capacity, expressiveness, and convergence properties. It addresses the crucial issue of interpretability, presenting theoretical approaches for understanding the inner workings of these models. Theoretical aspects of generalization are also explored, including overfitting, regularization techniques, and generalization bounds. By advancing theoretical understanding, this paper paves the way for informed model design, improved interpretability, and enhanced generalization in neural networks and deep learning, pushing the boundaries of their application in diverse domains. © 2023 IEEE.
date: 2023
publisher: Institute of Electrical and Electronics Engineers Inc.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85173043343&doi=10.1109%2fWCONF58270.2023.10235042&partnerID=40&md5=bdac334c46f1fe39a9595ff410135bf2
id_number: 10.1109/WCONF58270.2023.10235042
full_text_status: none
publication: 2023 World Conference on Communication and Computing, WCONF 2023
refereed: TRUE
isbn: 9798350311204
citation:   Usmani, U.A. and Usmani, M.U.  (2023) Theoretical Insights into Neural Networks and Deep Learning: Advancing Understanding, Interpretability, and Generalization.  In: UNSPECIFIED.