Yam

Feeling, Coding, Thinking

跳至内容

Home
Series
Archives
About
Projects

2020

Transformer 代码笔记

•

Attention
Decoder
Encoder
Multi-Head Attention
NLP
Self-Attention
Transformer

Luong Attention 论文+代码笔记

•

Attention
Luong Attention
NLP

Bahdanau Attention 论文笔记

•

Attention
Bahdanau Attention
NLP

2019

Transformer 论文笔记

•

Attention
NLP
Position-Encoding
Self-Attention
Transformer

Categories

Coding64
Feeling84
Thinking18

Music

Tag Cloud

AE AI ALBERT AR AUC Accuracy Activation Algorithm Array Arrow Attention Automatic Speech Processing Automation BERT BPE Backtracking Backward Bahdanau Attention Bart Bayes Beam Search Bert Bert-Flow Bi-LSTM Binary Search Blending Business C CCG CFG CKY CNN CRF CYK Calculus Camera Catalan ChatBot Chi2 Chunking Classification Cognition Collaborative Filtering Collins Parser Computational Linguistics Computer Computer Science Confusing Labels Context-Free Grammars Contrastive-Learning Coordinate Ascent Cosine Cosine Similarity Cross Entropy Cross-brackets Ctrl DB DNN DP Data Clearing Data Preprocess Data Science Data Structure Database DeBERTa Decoder Decoding Deep DeepGraph DeepLearning Dependence Diary Disentangled Attention DistilBERT Distillation Django Docker Docker-Compose Dockerfile Dropout Dynamic-Mask EDA EMD ERNIE Economics Edit Distance Efficient-DeepLearning Elasticsearch Electra Elixir Embedding Embeddings Encoder Entropy Evaluation F1 FDW FSM Feature Engineering Feature-based Few-Shot Fine-tuning Formal Grammars Forward Full-Text-Search Function Syntax Funk MF Funnel Transformer GBTD GELU GPT-2 GPU GRU GSG Gan Garden-path Git Glow Graceful Shutdown Gradient Descent Graph GraphQL Grid Grammar HMM Hard-SVM Hinge Loss IE IQR Imbalance Data Industry Information Extraction Information Theory Isolation Forest ItemCF Jaccard Java Jax Job Jupyter KKT KS Kernel Kernel Function Kernel Method Keyword Knowledge Graph LM LOF LR LSTM Language Model Lexical Semantics Lexicalism Lexicalized CFG Lexicalized Grammars Linear Algebra Linear Sturcture Linked List LinkedList Linux Logistic Regression Lucene Luong Attention MEMM MF Machine Machine Learning Machine Translation Manacher Managemnt Markov Materialized Views Math Matplotlib Matrix Factorization Median Metric Minimum Edit Distance Minkowski Model Evaluation Module Multi-Head Attention Multiway Tree NER NLG NLM NLP NLU NMT Naive Bayes Neo4j Ngram Normalizing Flow NumPy Numba Numpy Occupation Orientation P-R PCCG PCFG PEGASUS PPMI PTM PageRank Palindromic Pandarallel Pandas Partial Parsing Pearson Philosophy Phrase Structure Grammar Phrase Structure Grammars PoS Polars Pooling Position-Encoding Postgres Pragmatic Automatic Processing Pre-Trained Pre-Training Pre-training Precision Pretrain Pretrained Pretraining Probabilistic Grammar Probabilistic Model ProtoBERT Pruning Psychology PyPI Python Quant Quantization Query Queue R-Drop RELU RFE RMSE RNN ROC RaspberryPi Raspberrypi Recall Recommendation Recursion Reformer Regex Regular Expression Reinforcement Learning Relationship Extraction Representation Reqular Expressions RoBERTa Rotated Sorted Array Rust SCFG SGD SMO SQL SRN SVD++ SVM Seaborn Search Segmentation Self-Attention Semantic Automatic Processing Semantic Similarity Sentence Similarity Sentence-BERT Sentiment Classification Siamese Sigmoid SimCSE Similarity Simon Simpson Paradox Skill Slide Smoothing Soft-SVM Softmax Sort Spell Check SqueezeBERT Stack Stacking Statistics Stirling StratifiedKFold String Style Substring Summarization Supertagging Swap System TF-IDF Tagging TanH Test Text Generation Text Normalization TextCNN TextRank Thought Transformer Transformer-XL Tree Treebank Tuning Tutorial Ubuntu UniLM Unity Operation Unix UserCF Vagrant Valence Vector Semantics VirtualBox Visualization Viterbi Vocabulary Learning Voting WOE Web Server Multithreaded Server Wide Word2vec Work XLNet Z-Score ZhouZhihua Zipf binning few-shot ffmpeg jpype knowledge Graph motion node2vec ssh str vlc

Recents

在 TextCNN 上实验 Dropout 和对比学习
R-Drop
高性能数据处理
Git Memo
Docker Memo

Tags

© 2021 Yam All rights reserved.

Powered by Hexo