Classify the Lunar Rock:HackerEarth Data Science Competition

We are sorry to announce that the leaderboard for Classify the Lunar Rock:HackerEarth Data Science Competition now stands invalid.

This challenge was launched on October 1, 2019, and ended on October 31, 2019. Unfortunately, datasets for the challenge were readily available online. This led to several instances of malpractice.

As a result, we are reaching out to all participants who scored above 80 to share their source code files (.ipynb notebook, etc.) for the solution.

The last date of submissions for the same is December 20, 2019, 9 PM IST.

We apologize for the inconvenience caused and are working toward ensuring a fair judgement.

Problem statement

Lunar landings by renowned space stations across the world have yielded an abundance of new scientific data on the Moon. The various experiments placed on the surface provided information on seismic, gravitational, and other lunar characteristics. But perhaps the most dramatic result of the missions was returning a total of more than 800 pounds of lunar rock and soil for analysis on Earth. These samples of the Moon offered a deeper appreciation of the evolution of our nearest planetary neighbor. 

Imagine you have been called by one of the largest space stations in the world (XYZ) space station and you are requested to make a Machine Learning model which classifies the different rocks present on the moon's surface. The purpose of this is to make the research process a lot easier. This will reduce the human effort of doing a monotonous task.

In this dataset, you will find 7534 images of 2 sizes of lunar rocks. In the next 2 months, we challenge you to build models such that given an image, the model will predict the probability of every rock class.

Overview

Deep Learning is an application of Artificial Intelligence (AI) that provides systems with the ability to automatically learn and improve from experience without being explicitly programmed. Deep Learning is a science that determines patterns in data. These patterns provide deeper meaning to problems and help you to first understand problems better and then solve the same with elegance. HackerEarth’s Deep Learning challenge is designed to help you improve your Deep Learning skills by competing and learning from fellow participants.

Here’s presenting HackerEarth’s Deep Learning challenge—Classify the Lunar Rock in association with Dataquest.

Dataquest is an online education platform that teaches Data Science and programming skills right from your browser. Learn Python, R, SQL, Machine Learning, statistics, the command line, Git, Spark, Data Engineering, and much more. Our carefully-crafted course paths will provide you with skills that you need to work in Data Science even if you have no background in programming or statistics.

Dataquest's Deep Learning Fundamentals course ends with a guided project on image classification, and its other data science courses may also be helpful.

The prizes for the challenge are as follows

• 1st Prize - 250 USD +  6 months of free Premium subscription to Dataquest Courses

• 2nd Prize - 150 USD +  6 months of free Premium subscription to Dataquest Courses

• 2 Coral USB Accelerator (for participants currently residing in the US and Canada) + 6 months of free Premium subscription to Dataquest Courses

With this challenge, you can

• Learn and use the latest open-source libraries and packages

• Work on live problems because it excites you more than learning from books and tutorials

• Build your fan following in our community

• And of course, grab cash prizes

Who should participate?

• Working professionals

• Data Science/Machine Learning enthusiasts

• College students (if you understand the basics of predictive modeling)

Tutorials

• Machine Learning practice

• Image classification using Tensorflow

• Image classification using Keras

Note

• In order to claim your prizes, your HackerEarth profile must be completed more than 50%

• The prizes will be disbursed in the first week of the following month

• Ratings of the particular challenge will be updated in the user profile within 5 days after the challenge is over

1. Your output will be evaluated only for 50% of the test data while the contest is running. Once the contest is over, output for the remaining 50% of the data will be evalu...