注册并分享邀请链接,可获得视频播放与邀请奖励。

Assaf Ben Kish
@abk_tau
Deep Learning | Large Language Models | Reinforcement Learning
加入 August 2023
199 正在关注    298 粉丝
(1/7) Humans can acquire many capabilities without (catastrophically) forgetting previous ones. Why can't neural networks do the same? Local Support Learning (LSL) takes us a step closer towards this goal. In LLMs of up to 7B parameters, LSL augments gradient-based training to retain prior capabilities while learning new tasks at full capacity. Notably, it does so without access to prior data. Key idea: casting forgetting as a geometric problem, and optimizing for the worst case. Paper: Website and code:
显示更多
0
15
751
88
转发到社区