Just Keep Happy
“卷积+池化+激活+全连接” “卷积+池化+激活+全连接”
卷积 用它来进行特征提取 一个对象对一个系统连续做用一段时间后求系统的状态 形象化例子：https://www.zhihu.com/question/22298352/answer/1071892762?utm_source=qq&
2020-11-16 NN
Basic concept
AMBert AMBert
document.querySelectorAll('.github-emoji') .forEach(el => { if (!el.dataset.src) { return
2020-11-10 WeiRuoHe
AMBert AMBert
1.Explain Yourself! Leveraging Language Models for Commonsense ReasoningNazneen Rajani +2 authors R. Socher 2019, ACL
2020-11-10 WeiRuoHe
SpanBert SpanBert
Title《SpanBERT: Improving Pre-training by Representing and Predicting Spans》 Abstract ​ We present SpanBERT, a pr
2020-11-09 WeiRuoHe
NLP pre-training-model SpanBERT
K-Bert K-Bert
https://arxiv.org/pdf/1909.07606.pdf Title《K-BERT: Enabling Language Representation with Knowledge Graph》 Abstract Bert缺
2020-11-07 WeiRuoHe
NLP K-BERT pre-training-model
Pre-train-knowledge-graph Pre-train-knowledge-graph
document.querySelectorAll('.github-emoji') .forEach(el => { if (!el.dataset.src) { return
2020-11-07 WeiRuoHe
ssh-win10 ssh-win10
ssh远程登录linux系统（win10） 安装openssh 参考reference1. 输入ssh，如果出现下图的执行结果，则安装成功 通过ssh对远程linux系统进行访问(密钥加密）。 ssh -i 私钥位置 host@ip_
2020-11-03 Commontools
neo4j ssh
Extraction-rule-Morphological-Agreement Extraction-rule-Morphological-Agreement
document.querySelectorAll('.github-emoji') .forEach(el => { if (!el.dataset.src) { return
2020-10-30 PaperLookThroughy
NLP Extraction-rule
NN-to-LSTM NN-to-LSTM
Neural Network document.querySelectorAll('.github-emoji') .forEach(el => { if (!el.datase
2020-10-27 WeiRuoHe
BERT BERT
document.querySelectorAll('.github-emoji') .forEach(el => { if (!el.dataset.src) { return
2020-10-27 WeiRuoHe
BERT BERT
Title《**BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding**》 1.Abstract ​ We intro
2020-10-27 PaperLookThrough
NLP BERT Pre-training-model
nlp-word-model nlp-word-model
基于HMM的分词：​ 隐含马尔可夫模型（HMM）是将分词作为字在句子中的序列标注任务来实现的。其基本思路是：每个字在构造一个特定词语时都占据着一个特定的位置即词位，一般采用四结构词位：B（词首），M（词中），E（词尾）和S（单独成词）
2020-10-23 Model summary
Statistics
2 / 5