MLSP-1: Deep Learning Training Methods 1 |
Session Type: Poster |
Time: Tuesday, 8 June, 13:00 - 13:45 |
Location: Gather.Town |
Virtual Session: View on Virtual Platform |
Session Chair: Wenwu Wang, University of Surrey |
MLSP-1.1: META-LEARNING WITH ATTENTION FOR IMPROVED FEW-SHOT LEARNING |
Zejiang Hou; Princeton University |
Anwar Walid; Nokia Bell Labs |
Sun-Yuan Kung; Princeton University |
MLSP-1.2: B-SMALL: A BAYESIAN NEURAL NETWORK APPROACH TO SPARSE MODEL-AGNOSTIC META-LEARNING |
Anish Madan; IIIT Delhi |
Ranjitha Prasad; IIIT Delhi |
MLSP-1.3: DEEP TRANSFORM AND METRIC LEARNING NETWORKS |
Wen Tang; North Carolina State University |
Emilie Chouzenoux; CentraleSupélec |
Jean-Christophe Pesquet; CentraleSupélec |
Hamid Krim; North Carolina State University |
MLSP-1.4: ROBUSTNESS AND DIVERSITY SEEKING DATA-FREE KNOWLEDGE DISTILLATION |
Pengchao Han; Northeastern University |
Jihong Park; Deakin University |
Shiqiang Wang; IBM T. J. Watson Research Center |
Yejun Liu; Chongqing University of Posts and Telecommunications |
MLSP-1.5: ENSEMBLE DISTILLATION APPROACHES FOR GRAMMATICAL ERROR CORRECTION |
Yassir Fathullah; Cambridge University |
Mark J. F. Gales; Cambridge University |
Andrey Malinin; Yandex |
MLSP-1.6: TRAIN YOUR CLASSIFIER FIRST: CASCADE NEURAL NETWORKS TRAINING FROM UPPER LAYERS TO LOWER LAYERS |
Shucong Zhang; University of Edinburgh |
Cong-Thanh Do; Toshiba Research Europe Ltd. |
Rama Doddipatla; Toshiba Research Europe Ltd. |
Erfan Loweimi; University of Edinburgh |
Peter Bell; University of Edinburgh |
Steve Renals; University of Edinburgh |