exoushia Goto Github PK

automatic-leaf-infection-identifier

Automatic detection of plant diseases

bayesian_stats_rl_workshop

This is the repository containing all codefiles, data and output for the workshop

btp-public

Repository for BTP - amazonQA data

customer-churn-prediction

A ML problem from DataHack. Repository contains EDA + Feature selection & Engg + modelling using Logistic Regression

deploying-machine-learning-models

Code for the online course "Deployment of Machine Learning Models"

eda_projects

Exploratory data analysis , feature engg and data modelling on public datasets

hr-analytics-challenge---analytics-vidhya

"Can you predict which employee has a higher chance of getting promoted and help the help the organization to expedite the appraisal and promotion process?"

keras-super-resolution

Keras implementation of SrCNN as roposed by Dong et al "Image Super-Resolution Using Deep Convolutional Networks".

mavinai-misinformation-classifier

Omdena + Mavin AI news article misinformation and bias estimator

maze-traversing-bot

The code to guide a bot through a maze from a live overhead camera feed

mtp2

neural-networks

A basic ANN repository for understanding Neural networks without any black box approach

new-york-taxi-trip-duration-prediction

Ml problem from Datahack:

question_question_relatedness

st-dbscan

Implementation of ST-DBSCAN algorithm based on Birant 2007

web-page-classification---data-hack

Classification of Web page content is vital to many tasks in Web information retrieval such as maintaining Web directories and focused crawling which is used to selectively seek out web pages that are relevant to a pre-defined set of topics.

wine-quality-dataset-kaggle

Kaggle Dataset - on Wine Quality.

yolo_algorithm_using_keras

YOLO ("you only look once") is a popular algoritm because it achieves high accuracy while also being able to run in real-time. This algorithm "only looks once" at the image in the sense that it requires only one forward propagation pass through the network to make predictions. After non-max suppression, it then outputs recognized objects together with the bounding boxes.