Information Theory and Machine Learning

The recent successes of machine learning, especially regarding systems based on deep neural networks, have encouraged further research activities and raised a new set of challenges in understanding and designing complex machine learning algorithms. New applications require learning algorithms to be...

Full description

Saved in:
Bibliographic Details
Other Authors: Zheng, Lizhong (Editor), Tian, Chao (Editor)
Format: Electronic Book Chapter
Language:English
Published: MDPI - Multidisciplinary Digital Publishing Institute 2022
Subjects:
Online Access:DOAB: download the publication
DOAB: description of the publication
Tags: Add Tag
No Tags, Be the first to tag this record!

MARC

LEADER 00000naaaa2200000uu 4500
001 doab_20_500_12854_93254
005 20221025
003 oapen
006 m o d
007 cr|mn|---annan
008 20221025s2022 xx |||||o ||| 0|eng d
020 |a books978-3-0365-5308-5 
020 |a 9783036553078 
020 |a 9783036553085 
040 |a oapen  |c oapen 
024 7 |a 10.3390/books978-3-0365-5308-5  |c doi 
041 0 |a eng 
042 |a dc 
072 7 |a TB  |2 bicssc 
072 7 |a TBX  |2 bicssc 
100 1 |a Zheng, Lizhong  |4 edt 
700 1 |a Tian, Chao  |4 edt 
700 1 |a Zheng, Lizhong  |4 oth 
700 1 |a Tian, Chao  |4 oth 
245 1 0 |a Information Theory and Machine Learning 
260 |b MDPI - Multidisciplinary Digital Publishing Institute  |c 2022 
300 |a 1 electronic resource (254 p.) 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
506 0 |a Open Access  |2 star  |f Unrestricted online access 
520 |a The recent successes of machine learning, especially regarding systems based on deep neural networks, have encouraged further research activities and raised a new set of challenges in understanding and designing complex machine learning algorithms. New applications require learning algorithms to be distributed, have transferable learning results, use computation resources efficiently, convergence quickly on online settings, have performance guarantees, satisfy fairness or privacy constraints, incorporate domain knowledge on model structures, etc. A new wave of developments in statistical learning theory and information theory has set out to address these challenges. This Special Issue, "Machine Learning and Information Theory", aims to collect recent results in this direction reflecting a diverse spectrum of visions and efforts to extend conventional theories and develop analysis tools for these complex machine learning systems. 
540 |a Creative Commons  |f https://creativecommons.org/licenses/by/4.0/  |2 cc  |4 https://creativecommons.org/licenses/by/4.0/ 
546 |a English 
650 7 |a Technology: general issues  |2 bicssc 
650 7 |a History of engineering & technology  |2 bicssc 
653 |a supervised classification 
653 |a independent and non-identically distributed features 
653 |a analytical error probability 
653 |a empirical risk 
653 |a generalization error 
653 |a K-means clustering 
653 |a model compression 
653 |a population risk 
653 |a rate distortion theory 
653 |a vector quantization 
653 |a overfitting 
653 |a information criteria 
653 |a entropy 
653 |a model-based clustering 
653 |a merging mixture components 
653 |a component overlap 
653 |a interpretability 
653 |a time series prediction 
653 |a finite state machines 
653 |a hidden Markov models 
653 |a recurrent neural networks 
653 |a reservoir computers 
653 |a long short-term memory 
653 |a deep neural network 
653 |a information theory 
653 |a local information geometry 
653 |a feature extraction 
653 |a spiking neural network 
653 |a meta-learning 
653 |a information theoretic learning 
653 |a minimum error entropy 
653 |a artificial general intelligence 
653 |a closed-loop transcription 
653 |a linear discriminative representation 
653 |a rate reduction 
653 |a minimax game 
653 |a fairness 
653 |a HGR maximal correlation 
653 |a independence criterion 
653 |a separation criterion 
653 |a pattern dictionary 
653 |a atypicality 
653 |a Lempel-Ziv algorithm 
653 |a lossless compression 
653 |a anomaly detection 
653 |a information-theoretic bounds 
653 |a distribution and federated learning 
856 4 0 |a www.oapen.org  |u https://mdpi.com/books/pdfview/book/6152  |7 0  |z DOAB: download the publication 
856 4 0 |a www.oapen.org  |u https://directory.doabooks.org/handle/20.500.12854/93254  |7 0  |z DOAB: description of the publication