Space Engineering 3 Course Work at University of Sydney
-
Updated
Oct 8, 2017 - MATLAB
Space Engineering 3 Course Work at University of Sydney
[CVPR 2018] Tensorflow implementation of NAG : Network for Adversary Generation
A deep convolutional neural network is used to explain the results of another one (VGG19).
Adversarial Attack using a DCGAN
Tropical Sensitivity Scores
A Curated Microarrays Dataset of MDI-induced Differentiated Adipocytes (3T3-L1) Under Genetic and Pharmacological Perturbations
Universal Adversarial Audio Perturbations
Dark photon conversions in our inhomogeneous Universe. Code repository associated with the papers https://arxiv.org/abs/2002.05165 and https://arxiv.org/abs/2004.06733.
Code for the Adipocyte paper (Curated gene expression dataset of differentiating 3T3-L1 adipocytes under pharmacological and genetic perturbations)
Building a multi-label classifier from scratch and using transfer learning for the PASCAL VOC image dataset.
Perturbation experiments on the latent capsules of 3D Point Capsule Networks by Zhao et al.
Differentiable Optimizers with Perturbations in Pytorch
The MATLAB model here presented performs trajectory propagations based on the Constant Density Polyhedron algorithm. With this model, it is possible to compute trajectories in the proximity of astronomical bodies such as asteroids or comets. The algorithm also allows to compute ballistic trajectories.
[CVPR 2020] A Large-Scale Dataset for Real-World Face Forgery Detection
Code to analyze high-density EEG and concurrent EMG/EOG datastreams during balance perturbations (replicates results from https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6088363/)
Simulate the orbital motion for a CubeSat (HokieNav) as part of a senior design project with VT's ECE department sponsored by The Aerospace Corporation.
Code and raw data for the implementation of "Correction of human forehead temperature variations measured by non-contact infrared thermometer". Adrian Shajkofci, 2020
Fast Gradient Sign Method Adversarial Attack on Digit Recognition Model
In this work, we extend the FGSM method proposing multistep adversarial perturbation (MSAP) procedures to study the recommenders’ robustness under powerful methods. Letting fixed the perturbation magnitude, we illustrate that MSAP is much more harmful than FGSM in corrupting the recommendation performance of BPR-MF.
Repo of the paper "On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations"
Add a description, image, and links to the perturbations topic page so that developers can more easily learn about it.
To associate your repository with the perturbations topic, visit your repo's landing page and select "manage topics."