Open in app

Sign In

Write

Sign In

Mriganka Nath
Mriganka Nath

37 Followers

Home

About

Pinned

Domain Adaptation for Gravitational Lens finding| GSOC 22' @ ML4Sci

In this article, I’d like to share my GSOC experience and the lessons I learned. The learning journey with my mentors at ML4Sci was one of the best I’ve ever had; along with Machine Learning, Open-source and Astronomy, I learned a lot. In…

Astronomy

8 min read

Domain Adaptation for Gravitational Lens finding| GSOC 22' @ ML4Sci
Domain Adaptation for Gravitational Lens finding| GSOC 22' @ ML4Sci
Astronomy

8 min read


5 days ago

LLMs, for the win

You really have to live under some stone if you have not heard of or used ChatGPT. It has taken the world by storm with its very good (but often not so sure) responses. The goal of this article is to give an intuition about LLMs (Large Language Models), the…

Deep Learning

5 min read

LLMs, for the win
LLMs, for the win
Deep Learning

5 min read


Oct 17, 2021

Understanding ConvMixer (with a simple PyTorch implementation)

Recently in a tweet by Andrej Karpathy a paper has gone viral https://twitter.com/karpathy/status/1445915220644229124, where a model accomplishes two things together,1) crosses the 80% top1-accuracy in Imagenet 1k and 2) the whole model architecture actually fits in a tweet!! this was a paper titled “Patches Are All You Need?” where the…

Deep Learning

4 min read

Understanding ConvMixer (with a simple PyTorch implementation)
Understanding ConvMixer (with a simple PyTorch implementation)
Deep Learning

4 min read


Published in

Analytics Vidhya

·Sep 17, 2021

PyTorch Hooks

Sometimes there are many ways to do the same task. How you do it depends on the tools available and how efficient you are with them. Pytorch Hook is that tool, without which you may make a whole Neural Network and also train it, but when you know how powerful…

Deep Learning

5 min read

PyTorch Hooks
PyTorch Hooks
Deep Learning

5 min read


Published in

Analytics Vidhya

·Jul 1, 2021

Learning from different types of data, without supervision

Clive Humby, a British mathematician said that “ Data is the new oil” back in 2006. We all know now how precise this statement is. Then isn't limiting to only a single type of data restricting us from doing more complex tasks? We have created domains in deep learning like…

Deep Learning

7 min read

Learning from different types of data, without supervision
Learning from different types of data, without supervision
Deep Learning

7 min read


May 28, 2020

Behavioural Cloning

The self-driving car is considered as one of the next big things in the technology scene. …

Deep Learning

3 min read

Behavioural Cloning
Behavioural Cloning
Deep Learning

3 min read


Jul 16, 2019

Physics from Machine Learning’s perspective

If we see the starting of Science, it was with the people trying to understand their surroundings. This thirst of curiosity had done miracles to the ‘human’ revolution. With some theories dated back to the pre-Christ era starting with the Heliocentric theory, then came Galileo with his ideas and telescopes…

Machine Learning

3 min read

Physics from Machine Learning’s perspective
Physics from Machine Learning’s perspective
Machine Learning

3 min read

Mriganka Nath

Mriganka Nath

37 Followers

high dimensions go brrrrr; I work with Neural Networks;

Following
  • Ching (Chingis)

    Ching (Chingis)

  • Saranga Mahanta

    Saranga Mahanta

  • Chris Hughes

    Chris Hughes

  • Ágoston Török

    Ágoston Török

  • Chandrasikdar

    Chandrasikdar

See all (38)

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech

Teams