anirudhs123 Goto Github PK

attention-subnetworks-based-adversarial-detection

This work demonstrates an altogether different utility of attention heads. Self-attention heads are characteristic of Transformer models and have been well studied for interpretability and pruning, but here we build a novel adversarial detection model based on them.

cat-classifier

Demo App

draw-svg

Stanford CS248 Assignment 1: Implement a simple SVG renderer

home

HomE: Homography-Equivariant Video Representation Learning

indic-swipe

IndicSwipe is a collection of datasets and neural model architectures for decoding swipe gesture inputs on touch-based Indic language keyboards across 7 languages.

inter-iit-winning-solution

Winning solutions of Bridgei2i InterIIT Tech Meet 2021

music-instrument-classification

In this project we use a Lightweight-CNN based model to classify instruments from the Freesound audio data set. We make use of Mel-Spectrogram features from the input audio data as the input to the CNN model. To add robustness to the model, we use a novel data augmentation technique based on the Cut-Mix algorithm.

neural-recommender-system

This work involved building a pipeline of recommender systems comprising of Popularity based recommender, KNN similarity based Clustering recommender, Item-Item association based recommender, Bi-Partite graph based association recommender, Neural Graph based Collaborative Filtering and Neural Embedding based Collaborative filtering.

personal-site-anirudh-s

Personal Website of Anirudh S.

stanford-cs348n-assignment3-spring23

thermal-comfort-prediction-in-low-resourced-buildings

This work entails the usage of a novel hybrid deep transfer learning method for thermal comfort prediction in buildings with no or very little labelled data

trusglandsegmentation

Domain Generalization for Prostate Segmentation in Transrectal Ultrasound Images: A Multi-center Study