XufengXufengXufeng

Electra_with_tensorflow

This is an implementation of electra according to the paper {ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators}

try_gcn

try different opts on word context graph with GCN and GAT to obtain word embeddings.

Transformer_Regression_Application

This is an 'Attention is all you need' network application on non_nlp data.

Hand_code_ml

Trying to hand code ml algorithms.

k_lines

drawing K lines (绘制k线图)

BayesSpam

BayesSpam

crack_2048

trying to solve 2048 with AI.

dice-game

One guy plays dice the other guy guesses.

GA_for_param_tuning

Model_Explaination

Explain data by explaining models

Kaggle-Restaurant-VIsit

My solution to the Kaggle recruit restaurant visit forcast competition. It has a few boosting models and a nn model with entity embedding implemented with pytorch.

Kashgari

Simple, Keras-powered multilingual NLP framework, allows you to build your models in 5 minutes for named entity recognition (NER), part-of-speech tagging (PoS) and text classification tasks. Includes BERT, GPT-2 and word2vec embedding.

learning-functional-programming

functional programming has many benefits and python supports it.

Model_Free_RL

A simple illustration of q learning.

models

Models and examples built with TensorFlow

My-Rossmann-Solution

I have a predictive model for sales prediction. this has my favoirate featutre engineering practice data set.

predict-Sin-by-using-RNN

A simple RNN to predict time series data (sine).

Probabilistic-Programming-and-Bayesian-Methods-for-Hackers

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

Python

All Algorithms implemented in Python

Titanic

Trying different classifiers to get the highest predicting accuracy.

viz_animal

to visuaize animal size and longevity