Skip to content
View soumya-ch's full-sized avatar

Block or report soumya-ch

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
soumya-ch/README.md

Hi there 👋

I am Soumya, a Masters student at Stanford studying Computer Science. Previously, I completed my Bachelors in Computer Science and Engineering from IIT Bombay. I have spent time at Apple and Google Research working on problems in Natural Language Processing. I am also interested in Machine Learning Systems.

Visit my website to know more.

Pinned Loading

  1. flexflow/flexflow-train flexflow/flexflow-train Public

    Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training

    C++ 1.8k 245

  2. hyperbolic-label-emb-for-hmc hyperbolic-label-emb-for-hmc Public

    Code for the paper Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification (EACL '21)

    Python 23 5

  3. FGSM-Keras FGSM-Keras Public

    Implemention of Fast Gradient Sign Method for generating adversarial examples in Keras

    Jupyter Notebook 43 17

  4. infoseek infoseek Public

    Code for our AAAI 2021 paper "Model-agnostic Fits for Understanding Information Seeking Patterns in Humans"

    Python

  5. stanfordnlp/multi-distribution-retrieval stanfordnlp/multi-distribution-retrieval Public

    Code for our paper Resources and Evaluations for Multi-Distribution Dense Information Retrieval

    Python 15 1

  6. instrumental-music-translation instrumental-music-translation Public

    Course Project for Automatic Speech Recognition. Implemented music translation from one instrument to another using two approaches, different LSTM encoder-decoder based architectures and the other …

    Cuda