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
Fast PyTorch based DSP for audio and 1D signals
Python implementation of k-Shape with GPU support via PyTorch
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
Bonus materials, exercises, and example projects for our Python tutorials
Prompt tuning toolkit for GPT-2 and GPT-Neo
My ML research codebase
Code / solutions for Mathematics for Machine Learning (MML Book)
MonetDB/Postgres-Comparision
Multi-label Classification using PyTorch on the CelebA dataset.
Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019
The maven repository.
OOD Generalization and Detection (ACL 2020)
Robust evasion attacks against neural network to find adversarial examples
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
Open single and half precision gemm implementations
Deep Anomaly Detection with Outlier Exposure (ICLR 2019)
A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Make differentially private training of transformers easy
:bar_chart: Benchmark multiple object trackers (MOT) in Python
The "Python Machine Learning" book code repository and info resource
Tensors and Dynamic neural networks in Python with strong GPU acceleration
PyTorch-1.0 implementation for the adversarial training on MNIST/CIFAR-10 and visualization on robustness classifier.