Index Catalog // Arch : Northwestern University Institutional Repository

Description:: The past decade has seen the rapid progress of deep learning, which becomes a game-changing technique in different data-intensive domains, with the availability of large scale data, cost-effective computing hardware and more advanced learning theory and algorithms. Despite of the rapid progress of deep learning methods in daily-life applications, such...
Keyword:: Computational Photography, Representation Learning, Dataset Construction, Data Science, Computer Vision, and Deep Learning
Subject:: Materials Science, Information technology, and Computer science
Creator:: Jiang, Weixin
Owner:: Scholarly Digital Publishing
Language:: en
Date Uploaded:: 06/22/2022
Date Created:: 2022-01-01
Resource Type:: Dissertation
Alternate Identifier:: etdadmin_upload_899812 and http://dissertations.umi.com/northwestern:16024

Description:: Mammalian transcriptional regulation is well-known to be complex and highly context dependent. Different genetic and epigenetic features, including single nucleotide polymorphisms (SNPs) that function as cis- or trans-expression quantitative trait loci (eQTLs), transcription factor (TF) interaction profile with cis-regulatory elements (CREs), methylation of CpG dinucleotide sequences, and histone modification that...
Keyword:: Bioinformatics, Transcriptomics, Gene regulation, Deep Learning, Machine Learning, and Drug discovery
Subject:: Bioinformatics, Genetics, and Oncology
Creator:: Ji, Yanrong
Owner:: Scholarly Digital Publishing
Language:: en
Date Uploaded:: 06/28/2021
Date Created:: 2021-01-01
Resource Type:: Dissertation
Alternate Identifier:: etdadmin_upload_818497 and http://dissertations.umi.com/northwestern:15562

Description:: Recently, a myriad of applications take advantage of deep learning methods to solve regression/classification problems. Although deep neural networks have shown powerful learning capability, many deep learning applications suffer from the extremely time-consuming training of the neural networks. In order to reduce the training time, researchers usually consider parallel training...
Keyword:: Adaptive Batch Size, Data Parallelism, Deep Learning, and Communication Cost
Subject:: Computer engineering
Creator:: Lee, Sunwoo N/A
Owner:: Scholarly Digital Publishing
Language:: en
Date Uploaded:: 02/01/2021
Date Created:: 2020-01-01
Resource Type:: Dissertation
Alternate Identifier:: etdadmin_upload_772590 and http://dissertations.umi.com/northwestern:15340

Description:: Deep neural networks have achieved remarkable success in the past decade on tasks that were out of reach prior to the era of deep learning. Amongst the myriad reasons for these successes are powerful computational resources, large datasets, new optimization algorithms, and modern architecture designs. Most of the reasons are...
Keyword:: Statistical Physics, Deep Learning, and Machine Learning
Subject:: Statistical physics
Creator:: Wei, Mingwei
Owner:: Scholarly Digital Publishing
Language:: en
Date Uploaded:: 02/01/2021
Date Created:: 2020-01-01
Resource Type:: Dissertation
Alternate Identifier:: etdadmin_upload_777448 and http://dissertations.umi.com/northwestern:15367

LIBRARIES | ARCH