分布式

google DistBelief：Large Scale Distributed Deep Networks

画风迁移

• 1.Inceptionism: Going Deeper into Neural Networks

• 2.Perceptual Losses for Real-Time Style Transfer and Super-Resolution

• 3.Image Style Transfer using Convolutional Neural Networks

LSTM

基于RNN的LSTM架构：解决大词汇量语音识别

NLP

1.基于N-最短路径方法的中文词语粗分模型

2.基于角色标注的中国人名自动识别研究

L2R

机器学习及排序学习基础

条件随机场(CRF)

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

1.GBDT

Friedman <Greedy Function Approximation: A Gradient Boosting Machine>

陈天奇 Introduction to Boosted Trees

kdd2016: XGBoost: A Scalable Tree Boosting System

2.CTR平滑

Click-Through Rate Estimation for Rare Events in Online Advertising

3.神经网络

• 1.Yann LeCunGradient-based learning applied to document recognition

• 2.Yann LeCun+Bengio Convolutional networks for images, speech, and time series

• 3.Marcus Liwicki.. A Novel Approach to On-Line Handwriting Recognition Based on Bidirectional Long Short-Term Memory Networks

• 4.V. Dumoulin and F. Visin 深度学习卷积算法指南

• facebook: modout

word2vec

• A Closer Look at Skip-gram Modelling

• 1.Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean Efficient Estimation of Word Representations in Vector Space
• 2.Tomas Mikolov, Ilya Sutskever, Kai ChenDistributed Representations of Words and Phrases and their Compositionality

Sentence2Vec

From Word Embeddings To Document Distances

Distributed Representations of Sentences and Documents

Skip-Thought Vectors

Hierarchical Softmax

• Andriy Mnih, Geoffrey Hinton A Scalable Hierarchical Distributed Language Model

• 邱锡鹏 词嵌入与语言模型

LDA

• Parameter estimation for text analysis
• Blei:Latent Dirichlet Allocation
• Blei:Online learning for LDA

推荐系统

• 1.google news:Personalized News Recommendation Based on Click Behavior
• 2.google news:Google news personalization: scalable online collaborative filtering
• 3.google news:ppt: Google News Personalization
• 4.yahoo:Personalized Recommendation on Dynamic Content Using Predictive Bilinear Models

• 5.User profiles for personalized information access

• 7.Interweaving Trend and User Modeling for Personalized News Recommendation

• 8.Analyzing User Modeling on Twitter for Personalized News Recommendations

• 9.Open user profiles for adaptive news systems: help or harm?

• 微软:机器学习驱动下的内容分发和个性化推荐

• 视频:机器学习驱动下的内容分发和个性化推荐

• Applying deep learning to Related Pins

• The Wisdom of the Few:A Collaborative Filtering Approach Based on Expert Opinions from the Web

• Restricted Boltzmann Machines for Collaborative Filtering 目前Netflix使用的主要推荐算法之一

• LFM Factorization Meets the Neighborhood: a Multifaceted Collaborative Filtering Model

• Collaborative Filtering with Temporal Dynamics

• Context-Aware Recommender Systems

• Toward the next generation of recommender systems

• Information Seeking-Convergence of Search, Recommendations and Advertising

• Ad Click Prediction: a View from the Trenches

• Practical Lessons from Predicting Clicks on Ads at Facebook

• Performance of Recommender Algorithm on top-n Recommendation Task

• google:Improving User Topic Interest Profiles by Behavior Factorization
• google:youtube 2016: Deep Neural Networks for YouTube Recommendations 中文：YouTube基于深度神经网络的推荐系统
• google:Label Partitioning For Sublinear Ranking

LambdaMART

• Learning to Personalize Query Auto-Completion