At RBC Borealis, we believe Canada’s future as a world leader in artificial intelligence requires us to work together to bolster and grow the full Al ecosystem. By publishing open source code, we hope to help build a community rooted in mutual learning and collaboration.
Open Source Toolboxes 🧰
AdverTorch
Advertorch is a Python toolbox for adversarial robustness research. The primary functionalities are implemented in PyTorch. AdverTorch contains modules for generating adversarial perturbations and defending against adversarial examples, as well as scripts for adversarial training.
View ToolboxLiteTracer
LiteTracer acts as a drop-in replacement for argparse, and it can generate unique identifiers for experiments in addition to what argparse already does. Along with a reverse lookup tool, LiteTracer can trace-back the state of a project that generated any result tagged by the identifier.
View ToolboxPrivate Synthetic Data Generation
This toolbox provides machine learning practitioners with the ability to generate private and synthetic data samples from real world data.It currently implements 5 state of the art generative models that can generate differentially private synthetic data.
View ToolboxOur Popular Repositories
-
Noise_Flow
The codes for training and testing the Noise Flow model used for image noise modeling and synthesis.
Python
Get Code -
-
Flora-Opt
Official repository for the paper “Flora: Low-Rank Adapters Are Secretly Gradient Compressors” in ICML 2024.
Python
Get Code -
SLAPS-GNN
PyTorch code of “SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks”.
Python
Get Code
Responsible AI is key to the future of AI technology, science, development, and adoption.
Our RESPECT AI™ platform contributes knowledge, algorithms, programs, and tooling to help build technology that moves society forward.