加速100倍,性能媲美SOTA,浙大提出无数据知识蒸馏新方法FastDFKD O加速100倍,性能媲美SOTA,浙大提出无数据知... 2杭州·白鹭郡北 ​​​​

加速100倍,性能媲美SOTA,浙大提出无数据知识蒸馏新方法FastDFKD

在无法获取到原始训练数据的情况下,你可以尝试一下这种新型蒸馏算法 FastDFKD,数据合成与现有的生成方法相比...
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (OpenAI, 2020)
Paper: O网页链接
Abstract:
"We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent c ​​​​...展开全文c
Distributional Reinforcement Learning
Draft (under submission)
Marc G. Bellemare and Will Dabney and Mark Rowland: O网页链接 ​​​​
Congratulations!

Gongfan Fang, Kanya Mo, et al., Up to 100x Faster Data-free Knowledge Distillation
Jingwen Ye, Yining Mao, et al., Safe Distillation Box
Zunlei Feng, Jiacong Hu, et al., Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classif ​​​​...展开全文c
课题组方共凡同学领衔的拼图知识蒸馏工作被NeurIPS2021录用 2杭州·浙大玉泉 ​​​​
Algorithmic Bias and Data Bias: Understanding the Relation between Distributionally Robust Optimization and Data Curation
Agnieszka Słowik, Léon Bottou: O网页链接 2杭州·浙大玉泉 ​​​​

杭州·浙大玉泉

杭州市西湖区杭州植物园内
A Simple Framework for Contrastive Learning of Visual Representations (2020)
Paper: O网页链接 2杭州·浙大玉泉 ​​​​
Workshop on Foundation Models (of Deep Learning)
By Stanford University

O网页链接 2杭州·浙大玉泉 ​​​​

杭州·浙大玉泉

杭州市西湖区杭州植物园内
Perception is everything...
"Perceiver IO: A General Architecture for Structured Inputs & Outputs" (DeepMind 2021)
Paper: O网页链接 2杭州·浙江大学(玉泉校区) ​​​​

正在加载中,请稍候...