AIND Jupyter Notebook to predict student admissions using Keras Neural Networks

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

Adaptive Reinforcement Learning of curious AI basketball agents

Deeplearning4J框架搭建的第一个问答小AI

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

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

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.

Different types of word embedding for text processing

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.

Movie Recommendation System

Using random forest to predict Titanic passenger survival.

This is my contribution to a competition on kaggle.com, where you have a dataset with 79 explanatory variables describing (almost) every aspect of c. 1500 residential homes in Ames, Iowa. The aim is to predict the final price of each home.

This is the code for "Recurrent NeuralNetwork using keras and numpy" By M.Junaid Fiaz

Kaggle Challenge

Customer churn analysis for a telecommunication company

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

Generic encoding of record types

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.