Problem statement

Sneaky and slimy snakes have lately been creating a ruckus in your neighborhood. Two weeks ago, a toddler, crawling in the backyard, was bitten by one of them. But, thanks to the quick action of a few first-responders, the snakebite did not end up being fatal. Therefore, owing to the increasing number of such reported incidents, the local government body and wildlife rescue units have alerted the residents of your locality. Until the authorities find a resolution to this, a few tech-savvy neighbors have decided to build a smart reptile-monitoring system that detects snakes in security camera footage and alerts all households in the vicinity. As a Machine Learning expert, your job in the team is to build a sophisticated Deep Learning model that detects the breed of a snake from a given image.

Dataset

The dataset consists of over 5000 images of 35 varying breeds.

The benefits of practicing this problem by using Machine Learning/Deep Learning techniques are as follows:

• This challenge encourages us to apply your unsupervised Deep Learning skills to build a model that detects the breed of a snake from its image.
• This challenge helps us to enhance our practical knowledge of image processing, which is one of the advanced fields of Machine Learning and Artificial Intelligence.
• This challengs poses task of using small dataset and large number of classes.

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.

Why should you participate?

• To analyze and implement multiple algorithms and determine which is more appropriate for a problem
• To get hands-on experience in Machine Learning problems

Who should participate?

• Working professionals
• Data Science or Machine Learning enthusiasts
• College students (if you understand the basics of predictive modeling)

Necessary Tutorials:

• Machine Learning Tutorials

My Solution Pipelines:

• Solution with Only HackerEarth Data
• Solution with the Added AiCrowd Data [Score: 42.59]
• Solution with the Added AiCrowd Data [Score: 50.11]
• Solution with the Added AiCrowd Data [Score: 54.06]
• Solution with the Added CiCrowd Data [Score: 60.61]