Meta Learning - Learning to Learn


  • Machine Learning


Mentors :

  • Akshat Gupta

  • Tanay Sharma

  • Liza Dahiya

Mentees :

  • 6 students


Meta Learning is a recent advancement in the field of machine learning where we increase a level of abstraction and start ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป๐—ถ๐—ป๐—ด ๐˜๐—ผ ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป.

This helps us train neural networks with almost no data. In this project you shall first learn about the principles and applications of machine learning. Thereafter you shall understand the fundamentals of meta learning, i.e learning to learn. You will finally build a Few Shot image recognition network.

Preferred Skills : Inclination to Statistics, enthusiasm to learn The proposal must contain your skills and describe incidents which showcase your analytical skills.

References: https://data-notes.co/meta-learning-is-all-you-need-3bd0bafdf289 https://towardsdatascience.com/machine-learning-basics-part-1-a36d38c7916?gi=bf37f27f36b2


Tentative Timeline :

Week Number Tasks to be Completed
Week 1 Python and Basics of Machine Learning
Week 2 Learn deep learning frameworks
Week 3 Meta Learning and Implement Few Shot Image Classification and Image Recognition Network
Week 4 Read up the paper Model Agnostic Meta Learning and Implement it
Week 5 Complete and Document Everything