DATA Land

blog for data scientists

I usually post and archive my last GitHub project and online publications. feel free to contact me if need any help with content.

My technical post in data science

• History of Neural Networks! From Neurobiologists to Mathematicians 2020

• How to Become a Data Scientist? Step-by-step Path 2020

• All about hypothesis testing, from p-values to Z-test all-in-one 2019

My Github projects

• NLP
  • Classification and Vector Spaces
    • tweet sentiment analysis using Naive Bayes
    • tweet sentiment analysis using Logistic regression
    • Locality Sensitive Hashing
    • word translation from English to French
  • Probabilistic models
    • Auto Correct
    • Auto Complete
    • Continuous bag of words (CBOW) from scratch(Word Embedding)
  • Deep sequence models
    • Deep Auto Complete
    • Name Entity Recognition ________________________________
• Reinforcement learning
  • Bandit
    • epsilon-greedy
    • optimistic-greedy
  • DynamicProgramming
    • Policy Evaluation in Gridworld
    • Policy itteration in Gridworld
    • value iteration
  • MonteCarlo
    • MC policy evaluation
    • MC control
  • Temporal Difference
    • TD(0)
    • SARSA-acrobot
    • SARSA-Fozenlake
    • simple Q_learning for Taxi-v2
  • Deep Q_learning
    • simple deep Q_learning for Taxi-v2
    • simple deep Q_learning for LunarLander-v2 game
    • simple deep Q_learning for Pong
    • Double deep Q_learning(DDQN) for Pong
    • Dueling Double deep Q_learning(3DQN) for CartPole
  • PolicyGradient
    • Actor-Critic algorithm for cartPole
    • REINFORCE algorithm for cartpole ________________________________
• Deep Learning(tensorflow 2.2)
  • ANN
    • simple ANN (tutorial mode)
  • CNN
    • simple CNN for CIFAR10
    • simple CNN on fashion MNIST
  • RNN
    • LSTM and long term memory effect (tutorial mode)
    • RNN for image classification