What is Semi-Supervised Learning?
When you counter some real problem…
Data argumentation method - Attentive Cutmix & Cutmix
介紹兩篇對於data argumentation的技巧，Attentive CutMix和CutMix:
論文速速讀: CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE
Enriching Word Vectors with Subword Information
Transition-Based Parsing for Deep Dependency Structures
Leetcode -DFS BFS
請輸入密碼查詢加密文章
Sequence to Sequence Learning with Neural Networks
tags: study paper DSMI lab
paper: Sequence to Sequence Learning with Neural Networks
Abstract and Introduction
- DNN cannot be used to map sequences to sequences because they can only work when dimensionalty of input/output is fixed and known
- Task: English to French translation task from the WMT’14 dataset
- Proposed method 的優點:
- Minimal assumptions on the sequence structure: 甚麼樣的sequence 架構都可以處理
- Sensitive to word order
- Does well on long senetances