NerdTsai / my-notebook

My-notebooks

These are the notebooks what I have read for quick recall whenever I want to check sone points I have learned.

All IN CHINESE

1. Books&courses

Notebooks about books and courses I read.

1.1 Casuality

causality models reasoning and inference by Pearl.J

State :

• [Unfinished] chapter 1 : Introduction to Probabilities, Graphs, and Causal Models

1.2 Deep learning

Deep Learning

State :

• [Finished] chapter1 : Introduction
• [Finished] chapter2 : Linear Algebra
• [Finished] chapter3 : Probability and Information Theory
• [Finished] chapter4 : Numerical Computation
• [Finished] chapter5 : Machine Learning Basics
• [Finished] chapter6 : Deep Feedforward Networks
• [Finished] chapter7 : Regularization for Deep Learning
• [Finished] chapter8 : Optimization for Training Deep Models

1.3 PRML

Pattern Recognition and Machine Learning

State :

• [Unfinished] chapter1 : Introduction
  • Only 1.5 section
• [Finished] chapter2 : Probability Distributions
• [Finished] chapter8 : Graphical Models
• [Unfinished] chapter9 : Mixture Models and EM
• [Unfinished] chapter10 : Approximate Inference

1.4 Gaussian Process

Gaussian Processes for Machine Learning

State :

• [Unfinished] chapter2 : Regression

2. Papers

Notebooks of some important papers I have read about NLP and ML, DL

2.1 Deep learning

• SMASH: One-Shot Model Architecture Search through HyperNetworks
• Explanation of deep nerual network
• Structural Deep Embedding for Hyper-Networks
• Class Imbalance, Redux
• Sampling Matters in Deep Embedding Learning
• Training Very Deep Networks

2.2 Generative model

• Learning in Implicit Generative Models
• Neural Processes

2.3 Knowledge graph

• Learning Structural Node Embeddings via Diffusion Wavelets
• A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications
• On Inductive Abilities of Latent Factor Models for Relational Learning
• A Review of Relational Machine Learning for Knowledge Graphs
• Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach

2.4 Representation learning

• Hierarchical Density Order Embeddings
• Efficient Estimation of Word Representations in Vector Space
• Neural Word Embedding as Implicit Matrix Factorization
• Dependency-Based Word Embeddings
• Deep contextualized word representations
• Improved Word Representation Learning with Sememes
• Hubs in Space: Popular Nearest Neighbors in High-Dimensional Data

2.5 Application of graph neural network(GNN) in NLP

• Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
• Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
• Learning Deep Generative Models of Graphs
• Neural Relational Inference for Interacting Systems

2.6 Theory about graph neural network

• Relational inductive biases, deep learning, and graph networks

2.7 Research on language characteristics

• Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Path

2.8 Relation extraction

• Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks
• Neural Relation Extraction with Selective Attention over Instances
• Weakly-supervised Relation Extraction by Pattern-enhanced Embedding Learning
• CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases
• Learning with Noise: Enhance Distantly Supervised Relation Extractionwith Dynamic Transition Matrix
• Deep Residual Learning for Weakly-Supervised Relation Extraction
• Cross-Sentence N-ary Relation Extraction with Graph LSTM
• Distant Supervision for Relation Extraction beyond the Sentence

2.9 Casuality inference

• Causal Effect Inference with Deep Latent-Variable Models

2.10 Dialogue system

• Conversational Contextual Cues: The Case of Personalization and History for Response Ranking
• Neural Responding Machine for Short-Text Conversation

2.11 Coreference resolution

• Multi-Task Identification of Entities, Relations, and Coreference
• End-to-end Neural Coreference Resolution

2.12 Machine translation

• SOCKEYE : A Toolkit for Neural Machine Translation
• All You Need Is Attention

2.13 Machine reading

• Reinforced Mnemonic Reader for Machine Reading Comprehension
• Teaching Machines to Read and Comprehend

2.14 Entity alignment

• BIG-ALIGN: Fast Bipartite Graph Alignment
• Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks
• LinkNBed: Multi-Graph Representation Learning with Entity Linkage
• A Joint Embedding Method for Entity Alignment of Knowledge Bases
• Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding
• Iterative Entity Alignment via Joint Knowledge Embeddings
• Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment

3. Topics

3.1 About programing

• How to deal with big file
• Introduction about Chainer
• Introduction about Pandas
• Introduction about tensorflow
• Programing tricks in python
• Python mechanism
• Introduction about SQL

3.2 About machine learning

• Bagging, boosting
• Bayes error
• Befree
• Dropout
• Hessian matrix
• Imbalance data
• LSTMs
• MLE&MAP
• Regularation
• Semantics parsing
• Text similarity
• posterior&prior
• Convolution neural network
• Variational inference
• NER
• Inductive bias
• Lapalance matrix in network thermal conduction
• Lagrangian
• Spectral clustering
• Metrics