LEADER 03918nam 2200937z- 450 001 9910619463403321 005 20231214132951.0 010 $a3-0365-5308-8 035 $a(CKB)5670000000391640 035 $a(oapen)https://directory.doabooks.org/handle/20.500.12854/93254 035 $a(EXLCZ)995670000000391640 100 $a20202210d2022 |y 0 101 0 $aeng 135 $aurmn|---annan 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aInformation Theory and Machine Learning 210 $cMDPI - Multidisciplinary Digital Publishing Institute$d2022 215 $a1 electronic resource (254 p.) 311 $a3-0365-5307-X 330 $aThe 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. 606 $aTechnology: general issues$2bicssc 606 $aHistory of engineering & technology$2bicssc 610 $asupervised classification 610 $aindependent and non-identically distributed features 610 $aanalytical error probability 610 $aempirical risk 610 $ageneralization error 610 $aK-means clustering 610 $amodel compression 610 $apopulation risk 610 $arate distortion theory 610 $avector quantization 610 $aoverfitting 610 $ainformation criteria 610 $aentropy 610 $amodel-based clustering 610 $amerging mixture components 610 $acomponent overlap 610 $ainterpretability 610 $atime series prediction 610 $afinite state machines 610 $ahidden Markov models 610 $arecurrent neural networks 610 $areservoir computers 610 $along short-term memory 610 $adeep neural network 610 $ainformation theory 610 $alocal information geometry 610 $afeature extraction 610 $aspiking neural network 610 $ameta-learning 610 $ainformation theoretic learning 610 $aminimum error entropy 610 $aartificial general intelligence 610 $aclosed-loop transcription 610 $alinear discriminative representation 610 $arate reduction 610 $aminimax game 610 $afairness 610 $aHGR maximal correlation 610 $aindependence criterion 610 $aseparation criterion 610 $apattern dictionary 610 $aatypicality 610 $aLempel?Ziv algorithm 610 $alossless compression 610 $aanomaly detection 610 $ainformation-theoretic bounds 610 $adistribution and federated learning 615 7$aTechnology: general issues 615 7$aHistory of engineering & technology 700 $aZheng$b Lizhong$4edt$01319283 702 $aTian$b Chao$4edt 702 $aZheng$b Lizhong$4oth 702 $aTian$b Chao$4oth 906 $aBOOK 912 $a9910619463403321 996 $aInformation Theory and Machine Learning$93033697 997 $aUNINA