singlasahil14
I am a PhD student at the University of Maryland, College Park. My research interests are in robust and reliable machine learning.
University of MarylandCollege Park
Pinned Repositories
barlow
Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction
CASO
code for the paper https://arxiv.org/abs/1902.00407
CONV-SV
A fast and efficient way to compute a differentiable bound on the singular values of convolution layers
loss-exps
Experiments with different loss functions for image classification
orthogonal-convolution
Github repo for my experiments with the orthogonal convolution idea
resnet-exps
Experiments with center loss function for image classification on resnet architecture
salient_imagenet
Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?
SOC
Code for the ICML 2021 and ICLR 2022 papers: Skew Orthogonal Convolutions, Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100
sortpool2d
A new kind of pooling layer for faster and sharper convergence
style-transfer
style transfer code for generating stylized images using content and style loss from different layers, from different loss networks (vgg-16, vgg-19, inception-v1, inception-v2, inception-v3 trained on imagenet, inception-v3 trained on openimages, inception-v4
singlasahil14's Repositories
singlasahil14/sortpool2d
A new kind of pooling layer for faster and sharper convergence
singlasahil14/barlow
Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction
singlasahil14/salient_imagenet
Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?
singlasahil14/orthogonal-convolution
Github repo for my experiments with the orthogonal convolution idea
singlasahil14/loss-exps
Experiments with different loss functions for image classification
singlasahil14/SOC
Code for the ICML 2021 and ICLR 2022 papers: Skew Orthogonal Convolutions, Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100
singlasahil14/CASO
code for the paper https://arxiv.org/abs/1902.00407
singlasahil14/CONV-SV
A fast and efficient way to compute a differentiable bound on the singular values of convolution layers
singlasahil14/resnet-exps
Experiments with center loss function for image classification on resnet architecture
singlasahil14/word-language-model
word-language-model imported and modified from pytorch-examples
singlasahil14/fantastic-four
Code for the ICLR paper: https://openreview.net/forum?id=JCRblSgs34Z
singlasahil14/improved_l2_robustness
singlasahil14/so-robust
Code for ICML paper "Second-Order Provable Defenses against Adversarial Attacks"
singlasahil14/sparse-convolution
Code for sparse convolution written in C++
singlasahil14/data-augmentation
Code for fast data augmentation
singlasahil14/singlasahil14.github.io
singlasahil14/archai
Reproducible Rapid Research for Neural Architecture Search (NAS)
singlasahil14/cs224d-psets
cs224d (Deep learning for NLP) psets solutions
singlasahil14/dcd
Code for data-centric debugging paper
singlasahil14/ImageNetV2
A new test set for ImageNet
singlasahil14/improved_wgan_training
Code for reproducing experiments in "Improved Training of Wasserstein GANs"
singlasahil14/machine-learning-interview
Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.
singlasahil14/models
Models built with TensorFlow
singlasahil14/robust-apps
singlasahil14/robust_overfitting
singlasahil14/robust_representations
Code for "Learning Perceptually-Aligned Representations via Adversarial Robustness"
singlasahil14/robustness
A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.
singlasahil14/singlasahil14_old
singlasahil14/sngan_projection
GANs with spectral normalization and projection discriminator
singlasahil14/spoofing
ARP and DNS Spoofing