|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM336378815 |
| 003 |
DE-627 |
| 005 |
20231225232017.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3147798
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1121.xml
|
| 035 |
|
|
|a (DE-627)NLM336378815
|
| 035 |
|
|
|a (NLM)35104212
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Nguyen, Cuong
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a PAC-Bayes Meta-Learning With Implicit Task-Specific Posteriors
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 05.04.2023
|
| 500 |
|
|
|a Date Revised 05.04.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning. Our proposed method extends the PAC-Bayes framework from a single-task setting to the meta-learning multiple-task setting to upper-bound the error evaluated on any, even unseen, tasks and samples. We also propose a generative-based approach to estimate the posterior of task-specific model parameters more expressively compared to the usual assumption based on a multivariate normal distribution with a diagonal covariance matrix. We show that the models trained with our proposed meta-learning algorithm are well-calibrated and accurate, with state-of-the-art calibration errors while still being competitive on classification results on few-shot classification (mini-ImageNet and tiered-ImageNet) and regression (multi-modal task-distribution regression) benchmarks
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Do, Thanh-Toan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Carneiro, Gustavo
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 1 vom: 01. Jan., Seite 841-851
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:1
|g day:01
|g month:01
|g pages:841-851
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3147798
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 1
|b 01
|c 01
|h 841-851
|