Mathematics of Deep Learning : : An Introduction / / Leonid Berlyand, Pierre-Emmanuel Jabin.
The goal of this book is to provide a mathematical perspective on some key elements of the so-called deep neural networks (DNNs). Much of the interest in deep learning has focused on the implementation of DNN-based algorithms. Our hope is that this compact textbook will offer a complementary point o...
Saved in:
Superior document: | Title is part of eBook package: De Gruyter DG Plus DeG Package 2023 Part 1 |
---|---|
VerfasserIn: | |
Place / Publishing House: | Berlin ;, Boston : : De Gruyter, , [2023] ©2023 |
Year of Publication: | 2023 |
Language: | English |
Series: | De Gruyter Textbook
|
Online Access: | |
Physical Description: | 1 online resource (VI, 126 p.) |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
LEADER | 05122nam a22008775i 4500 | ||
---|---|---|---|
001 | 9783111025551 | ||
003 | DE-B1597 | ||
005 | 20230529101353.0 | ||
006 | m|||||o||d|||||||| | ||
007 | cr || |||||||| | ||
008 | 230529t20232023gw fo d z eng d | ||
010 | |a 2023931034 | ||
020 | |a 9783111025551 | ||
024 | 7 | |a 10.1515/9783111025551 |2 doi | |
035 | |a (DE-B1597)635280 | ||
035 | |a (OCoLC)1376935109 | ||
040 | |a DE-B1597 |b eng |c DE-B1597 |e rda | ||
041 | 0 | |a eng | |
044 | |a gw |c DE | ||
050 | 4 | |a Q325.73 |b .B47 2023 | |
072 | 7 | |a COM004000 |2 bisacsh | |
082 | 0 | 4 | |a 006.310151 |2 23 |
100 | 1 | |a Berlyand, Leonid, |e author. |4 aut |4 http://id.loc.gov/vocabulary/relators/aut | |
245 | 1 | 0 | |a Mathematics of Deep Learning : |b An Introduction / |c Leonid Berlyand, Pierre-Emmanuel Jabin. |
264 | 1 | |a Berlin ; |a Boston : |b De Gruyter, |c [2023] | |
264 | 4 | |c ©2023 | |
300 | |a 1 online resource (VI, 126 p.) | ||
336 | |a text |b txt |2 rdacontent | ||
337 | |a computer |b c |2 rdamedia | ||
338 | |a online resource |b cr |2 rdacarrier | ||
347 | |a text file |b PDF |2 rda | ||
490 | 0 | |a De Gruyter Textbook | |
505 | 0 | 0 | |t Frontmatter -- |t Contents -- |t 1 About this book -- |t 2 Introduction to machine learning: what and why? -- |t 3 Classification problem -- |t 4 The fundamentals of artificial neural networks -- |t 5 Supervised, unsupervised, and semisupervised learning -- |t 6 The regression problem -- |t 7 Support vector machine -- |t 8 Gradient descent method in the training of DNNs -- |t 9 Backpropagation -- |t 10 Convolutional neural networks -- |t A Review of the chain rule -- |t Bibliography -- |t Index |
506 | 0 | |a restricted access |u http://purl.org/coar/access_right/c_16ec |f online access with authorization |2 star | |
520 | |a The goal of this book is to provide a mathematical perspective on some key elements of the so-called deep neural networks (DNNs). Much of the interest in deep learning has focused on the implementation of DNN-based algorithms. Our hope is that this compact textbook will offer a complementary point of view that emphasizes the underlying mathematical ideas. We believe that a more foundational perspective will help to answer important questions that have only received empirical answers so far. The material is based on a one-semester course Introduction to Mathematics of Deep Learning" for senior undergraduate mathematics majors and first year graduate students in mathematics. Our goal is to introduce basic concepts from deep learning in a rigorous mathematical fashion, e.g introduce mathematical definitions of deep neural networks (DNNs), loss functions, the backpropagation algorithm, etc. We attempt to identify for each concept the simplest setting that minimizes technicalities but still contains the key mathematics. | ||
530 | |a Issued also in print. | ||
538 | |a Mode of access: Internet via World Wide Web. | ||
546 | |a In English. | ||
588 | 0 | |a Description based on online resource; title from PDF title page (publisher's Web site, viewed 29. Mai 2023) | |
650 | 0 | |a Deep learning (Machine learning) |x Mathematics. | |
650 | 4 | |a Faltungsneuronale Netze. | |
650 | 4 | |a Künstliche Neuronale Netze. | |
650 | 4 | |a Maschinelles Lernen. | |
650 | 4 | |a Tiefes Lernen. | |
650 | 7 | |a COMPUTERS / Intelligence (AI) & Semantics. |2 bisacsh | |
653 | |a Machine Learning, Deep Learning, Artificial Neural Networks (ANNs), Regression, Deep Neural Networks (DNNs),. | ||
700 | 1 | |a Jabin, Pierre-Emmanuel, |e author. |4 aut |4 http://id.loc.gov/vocabulary/relators/aut | |
773 | 0 | 8 | |i Title is part of eBook package: |d De Gruyter |t DG Plus DeG Package 2023 Part 1 |z 9783111175782 |
773 | 0 | 8 | |i Title is part of eBook package: |d De Gruyter |t EBOOK PACKAGE COMPLETE 2023 English |z 9783111319292 |
773 | 0 | 8 | |i Title is part of eBook package: |d De Gruyter |t EBOOK PACKAGE COMPLETE 2023 |z 9783111318912 |o ZDB-23-DGG |
773 | 0 | 8 | |i Title is part of eBook package: |d De Gruyter |t EBOOK PACKAGE Engineering, Computer Sciences 2023 English |z 9783111319124 |
773 | 0 | 8 | |i Title is part of eBook package: |d De Gruyter |t EBOOK PACKAGE Engineering, Computer Sciences 2023 |z 9783111318165 |o ZDB-23-DEI |
776 | 0 | |c EPUB |z 9783111025803 | |
776 | 0 | |c print |z 9783111024318 | |
856 | 4 | 0 | |u https://doi.org/10.1515/9783111025551 |
856 | 4 | 0 | |u https://www.degruyter.com/isbn/9783111025551 |
856 | 4 | 2 | |3 Cover |u https://www.degruyter.com/document/cover/isbn/9783111025551/original |
912 | |a 978-3-11-117578-2 DG Plus DeG Package 2023 Part 1 |b 2023 | ||
912 | |a 978-3-11-131912-4 EBOOK PACKAGE Engineering, Computer Sciences 2023 English |b 2023 | ||
912 | |a 978-3-11-131929-2 EBOOK PACKAGE COMPLETE 2023 English |b 2023 | ||
912 | |a EBA_CL_CHCOMSGSEN | ||
912 | |a EBA_CL_MTPY | ||
912 | |a EBA_DGALL | ||
912 | |a EBA_EBKALL | ||
912 | |a EBA_ECL_CHCOMSGSEN | ||
912 | |a EBA_ECL_MTPY | ||
912 | |a EBA_EEBKALL | ||
912 | |a EBA_ESTMALL | ||
912 | |a EBA_STMALL | ||
912 | |a GBV-deGruyter-alles | ||
912 | |a PDA12STME | ||
912 | |a PDA13ENGE | ||
912 | |a PDA18STMEE | ||
912 | |a PDA5EBK | ||
912 | |a ZDB-23-DEI |b 2023 | ||
912 | |a ZDB-23-DGG |b 2023 |