Seasons Of Code
Meta Learning - Learning to Learn • Akshat Gupta, Tanay Sharma, Liza Dahiya
WnCC - Seasons of Code
Seasons of Code is a programme launched by WnCC along the lines of the Google Summer of Code. It provides one with an opprtunity to learn and participate in a variety of interesting projects under the mentorship of the very best in our institute.
List of Running Projects
- Browser Based PDF manager
- Resume Script Generator
- Physicc : A Simple Physics Engine
- Image Colorization
- Language Model Based Syntax Autocompletion in a Text Editor
- Computer vision based web app
- Cribbit Cribbit (Open for PGs Only)
- Techster Texter
- Language Detection
- Book Tracker
- ResoBin - Not the bin we deserve but the bin we need!
- Moodify
- Agree to disagree
- Unscripted
- Watson (World's smartest assistant in your pocket)
- IITinder
- BriefKing
- Meta Learning - Learning to Learn
- Break free of the matrix, by building one!
- Procedurally Generated Infinite Open World
- Introduction to App Development
- PAC MAN
- Introduction to Web Development
- (Un)Clear
- Goal ICPC
- Traffic congestion modelling and rendering
- PyRated
- Tools for Data Science
- Machine Learning Based Metropolitan Air Pollution Estimation
- Audio controlled drone
- NLPlay with Transformers
- DIY FaceApp
- A Deep Dive into CNNs
- Competitive Coding
- Snake AI
- Facial Recognition App
- Gaming meets AI !!!
- R(ea)L Trader
- Computational Geometry
- Deep reinforcement learning - 2048 AI
- Reinforcement Learning to Finance
- Developing Hybrid ANN-Statistical Model for Robust Stock Market Prediction
- Si-Phy
- Astronomical Data-modelling and Interpretation
- Visual Perception for Self Driving Cars
- Convolutional Neural Networks and Applications
- Quantum Computing Algorithms
- Algorithm Visualizer
- Anime Club IITB Website using Django
- Machine Learning in Browser
Meta Learning - Learning to Learn
The Input to this application will be “your daily class lectures” and the expected output is a brief but detailed summary of the entire lecture.
No. of mentees: 6
Meta Learning is a recent advancement in the field of machine learning where we increase a level of abstraction and start 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝘁𝗼 𝗟𝗲𝗮𝗿𝗻. 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 Project 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 |