Basic Deep Learning Task

Overview

• These are useful projects for beginners and intermediates to approaching Deep Learning. Each ipynb file is a different topic (lesson).
• Dependency: Python and some other libraries are listed in each document (ipynb files).

Implementation

1. Natural language processing project: Exploratory data analysis, pre-process, classification models, unsupervised technique, including GridSearchCV, topic modeling (Author_Classification.ipynb).
   • Pre-process:
     • Bag of word.
     • Term Frequence-Inverse Document Frequency.
     • Word to vector.
   • Classification:
     • Naive Bayes.
     • Logistic Regression.
     • Decision Tree
     • Random Forest.
     • K - Nearest Neighbors.
     • Supoprt Vector Machine
     • Gradient Boosting.
     • Recurrent Neural Networks.
   • Unsupervised technique:
     • K - Means.
     • Agglomerative.
     • Gaussian Mixture.
   • Topic modeling:
     • Latent Dirichlet Allocation.
     • Latent Semantic Analysis.
     • Non-Negative Factorization
2. Image processing project: Exploratory data analysis and fruit classification with Convolution and LSTM (Fruit_Classification.ipynb).
3. Natural language processing project: Exploratory data analysis, pre-process, apply sequence to sequence and BERT models to data(Watson_project.ipynb).
4. Natural language processing project: Rule-based chat bot with TD-IDF and Bag of words(Chatbot.ipynb).

Maintainers

• Tran Dang Trung Duc