Skip to content
You must be logged in to sponsor digantamisra98

Become a sponsor to Xa9aX ツ

Hi there!

I'm Diganta Misra, founder of a research group Landskape and Machine Learning Engineer at Weights & Biases. I'm also an incoming MSc in CS (Machine Learning specialization) at MILA, Montreal affiliated with UdeM and a Visiting Research Scholar at VITA, UT Austin. I mostly focus on Abstract Algebra, Computer Vision, Mean Field Theory, Continual Learning, Convex Optimization, Deep Learning Theory and Non-Linear Dynamics.

As an open-source and reproducibility enthusiast, I aim to make current research in deep learning more transparent, reproducible and accessible. Landskape is a non-profit research org that I founded to provide a platform to students and like-minded professionals to explore research ideas of common interests for understanding deep neural networks.

Running an organization as well as working on reproducibility comes with financial and compute requirements. With GitHub sponsors, it will allow me to continue with my efforts in this domain and also fund my research.

My current research interest is to make sparse models cool and also have large scale robust models. As of right now, I am working on theory of robustness in deep learning.

I also want to make a podcast where I interview less well-known authors whose works are leaving an imprint in various domains of deep learning and debunk their papers along with them from a theoretical, applied and reproducibility perspective.

3 sponsors have funded digantamisra98’s work.

@digantamisra98

With $250 a month, I'll be able to start off with running consistent reproducible experiments on robustness at large scale

Private Sponsor
@SparshaMishra
@taskswithcode

Featured work

  1. digantamisra98/Mish

    Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]

    Jupyter Notebook 1,291
  2. digantamisra98/Echo

    Python package containing all custom layers used in Neural Networks (Compatible with PyTorch, TensorFlow and MegEngine)

    Python 137
  3. digantamisra98/EvoNorm

    Unofficial PyTorch Implementation of EvoNorm

    Python 121
  4. digantamisra98/Reproducibilty-Challenge-ECANET

    Unofficial Implementation of ECANets (CVPR 2020) for the Reproducibility Challenge 2020.

    Python 32

0% towards $250 per month goal

Be the first to sponsor this goal!

Select a tier

$ a month

You'll receive any rewards listed in the $10 monthly tier. Additionally, a Public Sponsor achievement will be added to your profile.

$10 a month

Select
  • Aid my addiction for caffeine☕
  • Support my buying frenzy of one pure math book a month to read 📘

$50 a month

Select
  • Pays most of my internet bill a month 📶

$100 a month

Select
  • Support the add-ons software licensing costs used for research at Landskape 👨‍💻
  • Support storage costs on AWS/ GCP 💾

$350 a month

Select
  • Helps running one/ two ImageNet experiments on AWS 🧪

$1,500 a month

Select
  • Large scale hyper-parameter sweeps for ImageNet models on AWS/ GCP ☁️
  • Large scale robustness stress testing of deep networks ⌛

$5,000 a month

Select

Umm, thanks, I guess 😅