# 2019년 AI & 머신러닝 분야 주요 논문 Top 10

> Clean Markdown view of GeekNews topic #944. Use the original source for factual precision when an external source URL is present.

## Metadata

- GeekNews HTML: [https://news.hada.io/topic?id=944](https://news.hada.io/topic?id=944)
- GeekNews Markdown: [https://news.hada.io/topic/944.md](https://news.hada.io/topic/944.md)
- Type: news
- Author: [xguru](https://news.hada.io/@xguru)
- Published: 2019-11-21T09:59:48+09:00
- Updated: 2019-11-21T09:59:48+09:00
- Original source: [topbots.com](https://www.topbots.com/top-ml-research-papers-2019/)
- Points: 3
- Comments: 0

## Topic Body

올해 AI 부분에서 가장 의미있는 10개의 논문을 추리고, 각 논문의 요약, 주요 성취, AI 커뮤니티들의 반응 및 수상내역, 관련한 미래 추가 연구영역, 적용가능한 비즈니스 분야, 구현 코드 위치 등을 정리.

1. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

2. Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations

3. Meta-Learning Update Rules for Unsupervised Representation Learning

4. On the Variance of the Adaptive Learning Rate and Beyond

5. XLNet: Generalized Autoregressive Pretraining for Language Understanding

6. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

7. Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

8. A Theory of Fermat Paths for Non-Line-of-Sight Shape Reconstruction

9. Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning

10. Learning Existing Social Conventions via Observationally Augmented Self-Play

## Comments



_No public comments on this page._