The remarkable Papers I have read
Contents
The initial intent to write this blog is to sorting out the paper I read in 2018. As the AI area is changing and new techs are coming up every minute, so I want myself to keep up to date of the remarkable papers. Stay hungry, stay foolish.
The papers mainly can be divided in several eras: utils of Data science, Machine Learning, Reinforcement Learning, Computer Vision, deep learning. And each can be divided into more specific era. If you are a recruiter, happy to be asked about them or discuss about them.
Deep Learning
Utils of DL
- Understanding the difficulty of training deep feedforward neural networks
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Deep Residual Learning for Image Recognition
RNN
- Visualizing and Understanding Recurrent Networks
Reinforcement Learning
PG related
- Policy Gradient Methods for Reinforcement Learning with Function Approximation
- Trust Region Policy Optimization
- Asynchronous Methods for Deep Reinforcement Learning
- Proximal Policy Optimization Algorithms
MCTS
- Mastering the game of Go with deep nerual networks and tree search
- Mastering the game of Go without human knowledge
Machine Learning
Utils of ML
- Exploratory Understanding for Class-Imbalance Learning
- SMOTE: Synthetic Minority Over-sampling Technique
- Leakage in Data Mining: Formula, Detection, and Avoidance
- Term Paper: How and Why to Use stochastic Gradient Descent?
TreeS and tree based
- lightGBM: A Highly Efficient Gradient Boosting Decision Tree
- XGBoost: A Scalable Tree Boosting System
SVM
- A Practical Guide to Support Vector Classification
Clustering
- A Density-based Algorithm for Discovering Clusters in Large Spatial Databases with Noise
Project Reference Papers
- Deep Learning for Identifying Breast Cancer
- Resource Management with Deep Reinforcement Learning
- Customized Regression Model for Airbnb Dynamic Pricing
todo
- Relational inductive biases, deep learning, and graph networks