Jacobian-Free Backprop

Associated Publication

JFB: Jacobian-Free Backpropagation for Implicit Models (arXiv Link)

@article{WuFung2022JFB,
    title={JFB: Jacobian-Free Backpropagation for Implicit Models},
    author={Fung, Samy Wu and Heaton, Howard and Li, Qiuwei and McKenzie, Daniel and Osher, Stanley and Yin, Wotao},
    journal={Proceedings of the AAAI Conference on Artificial Intelligence},
    year={2022}
}

Set-up

Install all the requirements:

pip install -r requirements.txt

Training

For each dataset, there are three types of training drivers:

FPN with our proposed backprop:

	python train_CIFAR10.py
	python train_CIFAR10_Unaugmented.py
	python train_MNIST.py
	python train_SVHN.py

FPN with Jacobian-based backprop:

	python train_CIFAR10_Jacobian_Based.py
	python train_CIFAR10_Unaugmented_Jacobian_Based.py
	python train_MNIST_Jacobian_Based.py
	python train_SVHN_Jacobian_Based.py

Explicit models.

	python train_CIFAR10_Explicit.py
	python train_CIFAR10_Unaugmented_Explicit.py
	python train_MNIST_Explicit.py
	python train_SVHN_Explicit.py

JFB: Jacobian-Free Backpropagation for Implicit Models

Related tags

Overview

Jacobian-Free Backprop

Associated Publication

Set-up

Training

Owner

Typal Research

yolox_backbone is a deep-learning library and is a collection of YOLOX Backbone models.

Applying curriculum to meta-learning for few shot classification

Airbus Ship Detection Challenge

Official implementation of the method ContIG, for self-supervised learning from medical imaging with genomics

Complete* list of autonomous driving related datasets

SASM - simple crossplatform IDE for NASM, MASM, GAS and FASM assembly languages

Earth Vision Foundation

Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning

Sketch-Based 3D Exploration with Stacked Generative Adversarial Networks

public repo for ESTER dataset and modeling (EMNLP'21)

Machine learning notebooks in different subjects optimized to run in google collaboratory

'Solving the sampling problem of the Sycamore quantum supremacy circuits

This python-based package offers a way of creating a parametric OpenMC plasma source from plasma parameters.

Reinforcement Learning for the Blackjack

Teaching end to end workflow of deep learning

CNN Based Meta-Learning for Noisy Image Classification and Template Matching

An end-to-end project on customer segmentation

Source code and notebooks to reproduce experiments and benchmarks on Bias Faces in the Wild (BFW).

Neural Factorization of Shape and Reflectance Under An Unknown Illumination

Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations