chrhenning/hypercl
Continual Learning with Hypernetworks. A continual learning approach that has the flexibility to learn a dedicated set of parameters, fine-tuned for every task, that doesn't require an increase in the number of trainable weights and is robust against catastrophic forgetting.
PythonApache-2.0
Stargazers
- aGiant
- AlanChouSynopsys
- andrewczgithub
- AuCsonUniversity of Southern California
- BentengMa
- btwardowComputer Vision Center, UAB
- caoxu915683474@Lenovo Reasearch@BIT
- ChunyunShen
- DarrenZhang01University of Toronto
- fly51flyPRIS
- harsh0709
- JohswaldZurich
- JosephKJAdobe Research
- juliagusak
- lebriceMila - Quebec Artificial Intelligence Institute @mila-iqia
- likemoonlight
- likesiwellCASIA
- liuyudutDLUT
- lrigaziocupertino
- mawbrayImperial College London
- moskomuleRIKEN AIP
- nkdnnlrUniversity of Hertfordshire and Western Sydney University
- philip-huangPittsburgh, USA
- radao@scythe-robotics
- rguo12London
- saulgoodenoughShanghai, China
- smonsaysETH Zurich
- taolichengMila @mila-iqia, Université de Montréal
- TGHead
- vanzytayGoogle
- voidismCSAIL, MIT
- wangxu-scu
- wutong8023Southeast University; Monash University
- Xi-LCity University of Hong Kong
- yangzhaonan18深圳
- zhouchunpongZJU