Google Street View House Number(SVHN) Dataset, and classifying them through CNN

A command-line utility program for automating the trivial, frequently occurring data preparation tasks: missing value interpolation, outlier removal, and encoding categorical variables.

Demo on the capability of Yandex CatBoost gradient boosting classifier on a fictitious IBM HR dataset obtained from Kaggle. Data exploration, cleaning, preprocessing and model tuning are performed on the dataset

Analysis and preprocessing of the kdd cup 99 dataset using python and scikit-learn

Adaptive Reinforcement Learning of curious AI basketball agents

This repository contains Sentiment Classification, Word Level Text Generation, Character Level Text Generation and other important codes/notes on NLP. Python and Keras are used for implementation.

Semantic Segmentation Using U-Net Architecture

Deeplearning4J框架搭建的第一个问答小AI

Keras 응용(CNN, RNN, GAN, DNN, ETC...) 사용법 예시

Movie Recommendation System

one hot encoding using numpy, sklearn, and keras. Created Date: 7 Jan 2019

Machine-learning models to predict whether customers respond to a marketing campaign

Customer churn analysis for a telecommunication company

To predict whether booked appointment will be completed or it will be no show.

Implementation of Character level CNN

Feature Importance of categorical variables by converting them into dummy variables (One-hot-encoding) can skewed or hard to interpret results. Here I present a method to get around this problem using H2O.

Determining the housing prices of California properties for new sellers and also for buyers to estimate the profitability of the deal.

Generic encoding of record types

Deep Neural Networks like Single Layer Perceptron and Multi Layer Perceptron implementation using Tensorflow library on Datasets like MNIST and Naval Mine for categorical Classification. Saving and Restoring Tensorflow "Variables" weights for testing.

Kaggle Challenge