Anirudh Sriram's repositories
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
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.
Personal-Site-Anirudh-S
Personal Website of Anirudh S.
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
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
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.
TRUSGlandSegmentation
Domain Generalization for Prostate Segmentation in Transrectal Ultrasound Images: A Multi-center Study