Name: Adam Dziedzic
Type: User
Company: The University of Toronto & Vector Institute
Bio: I'm a researcher, engineer, software developer, and systems designer. I have a passion for machine/deep learning,technology, databases, traveling, sport & music
Location: Toronto
Blog: adam-dziedzic.github.io
Adam Dziedzic's Projects
Walkthroughs for DSL, AirSim, and the Vector Institute
Adam Dziedzic's personal website.
Creating and defending against adversarial examples
Countering Adversarial Image using Input Transformations.
Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
An open-source NLP research library, built on PyTorch.
Analysis by Synthesis — reimplemented
Official Pytorch Implementation of: "Asymmetric Loss For Multi-Label Classification"(2020) paper
autodp: A flexible and easy-to-use package for differential privacy
An awesome list of papers on privacy attacks against machine learning
Band-limited Training and Inference for Convolutional Neural Networks
BattleShips
A polystore database from researchers of the Intel Science and Technology Center for Big Data
capc-demo
Top 1 solution of Chexpert
An adversarial example library for constructing attacks, building defenses, and benchmarking both
Coding exercises.
convex1
Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes
A few cuda examples built with cmake
A website for a project - example.
Code samples for CV2.
pytorch implementation of Parametric Noise Injection for adversarial defense
Convolutional Neural Networks
Example projects I completed to understand Deep Learning techniques with Tensorflow.
This repository contains implementations and illustrative code to accompany DeepMind publications