Name: Daniel Severo
Type: User
Company: FAIR, Vector Institute, and UToronto
Bio: Information Theory and Machine Learning
Twitter: _dsevero
Location: Toronto, Canada
Blog: dsevero.com
Daniel Severo's Projects
Mathematical proof of functionality, of a highly efficient pseudo-random number generator: The Ziggurat Method
An adversarial example library for constructing attacks, building defenses, and benchmarking both
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
Confirmed cases of COVID-19 in Brazil
Compression tools for machine learning researchers
Data Structures and Algorithms for fun
Parallel computing with task scheduling
Distributed and parallel machine learning
LaTeX files for the Deep Learning book notation
Source code for my personal website.
Source code for personal homepage
enum/enum34 compatibility package
My Personal Website based on the Hugo Academic theme
Conditional Independence Testing with Generative Adversarial Networks
Repository for self-teaching of Generative Models and its applications.
PyTorch implementation of LEARNING LATENT PERMUTATIONS WITH GUMBEL-SINKHORN NETWORKS
The holdout randomization test: feature selection using black box predictive models
Implementation of Action Matching
A Graph Neural Network Library in Jax
Reference deployment of JupyterHub with docker
Code for "The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric"
Official code accompanying the arXiv paper Compressing Multisets with Large Alphabets
A collection of tools for neural compression enthusiasts.
A distributed consensus mechanism for securing content novelty: Proof of Novelty.
Python MIDI library
Pytorch Lightning code guideline for conferences
Code for "Random Edge Coding: One-Shot Bits-Back Coding of Large Labeled Graphs"
Regularized Classification-Aware Quantization