About Us

We discover and learn the models and practices used in cutting-edge research projects around the world by implementing research papers.

Teaching sessions are occasionally conducted wherein we explain and implement concepts to acquaint newcomers to the field of data science.

Kaggle Competition Details

Presentation: http://bit.ly/neuraldotppt

Ask Us Questions: https://bit.ly/neuraldotq

Code - Introduction To Python: https://bit.ly/neuraldotpython

Code - Convolution: https://bit.ly/neuraldotcon

Code - MNIST: https://bit.ly/neuraldotmnist

Kaggle Competition: http://bit.ly/neuraldotkaggle

Sample Python Notebook for Kaggle Competition https://bit.ly/neuraldotsample

The teams will be taught the fundamentals of Machine Learning and Python programming in order to implement a handwriting recognition model. This includes the basics of image processing and using GPU enabled services like Google Colab. They will then be given a different dataset and compete in creating the best performing Machine Learning model with the tools previously taught.

Abstract

With each passing day telescopes around and above the Earth capture more and more images of distant galaxies. As better and bigger telescopes continue to collect these images, the datasets begin to explode in size. In order to better understand how the different shapes of galaxies relate to the physics that create them, such images need to be sorted and classified.

Image Credit: ESA/Hubble & NASA

Galaxies in this set have already been classified once through the help of hundreds of thousands of volunteers, who collectively classified the shapes of these images by eye in a successful citizen science crowdsourcing project. However, this approach becomes less feasible as data sets grow to contain of hundreds of millions (or even billions) of galaxies. That's where you come in.

This competition asks you to analyze the JPG images of galaxies to find automated metrics that reproduce the probability distributions derived from human classifications. For each galaxy, determine the probability that it belongs in a particular class. Can you write an algorithm that behaves as well as the crowd does?

Round 1 - Hands-on Briefing Session

Teams will be taught the fundamentals of Machine Learning and Python for ML through the implementation of a handwriting recognition model.

  • Types of Learning : Supervised, Unsupervised, Reinforcement, Deep Learning etc.
  • Data Preprocessing : Image convolution, Slicing, Kernels etc.
  • Python Basics : Important libraries, Helper functions.
  • Implementation : Demo of a hand written number recognition model (Input - Image, Output - Label)

Round 2 - Competition

The teams will be given a labelled dataset and are expected to train the ML model to identify and label the given image.

  • Aim : To train the ML model on the given dataset.
  • Model Objective : Input - Picture, Output - Labelled Image.