Data

Tools

Indexes

Applications

Experiments

Open Source Science

diff-ml

Second-Order Differential ML

https://github.com/neilkichler/diff-ml

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.4%) to scientific vocabulary

Keywords

differential-machine-learning equinox jax sobolev-training
Last synced: 10 months ago · JSON representation ·

Repository

Second-Order Differential ML

Basic Info
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
differential-machine-learning equinox jax sobolev-training
Created almost 3 years ago · Last pushed about 2 years ago
Metadata Files
Readme License Citation

README.md

Second-Order Differential Machine Learning

For detailed background information, consider looking into:

https://neilkichler.github.io/master-thesis/Thesis.pdf

Notebooks

The notebooks contain the majority of the code right now and accumulate the ideas that are needed for the proposed methods. The package currently implements the core functions needed for Sobolev Training / Differential Machine Learning.

Installation

Clone the repo and execute the following inside the root folder.

bash python -m pip install -e .

Requires Python 3.9+, JAX 0.4.16+ and Equinox 0.10.5+.

Development

We use Hatch as the project manager. The usual commands apply.

Show all available scripts

bash hatch env show

Run case study

bash hatch -e example run python examples/bachelier/bachelier.py

Run Tests

bash hatch run test:test

Build project wheel

bash hatch build

Lint project

bash hatch run lint:fmt

Owner

  • Name: Neil Kichler
  • Login: neilkichler
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
title: Second-Order Differential Machine Learning using Jax
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Neil
    family-names: Kichler
    email: neil.kichler@rwth-aachen.de
    affiliation: RWTH Aachen
repository-code: 'https://github.com/neilkichler/diff-ml'
abstract: TODO
keywords:
  - jax
  - differential-machine-learning
  - neural-networks
license: MIT
commit: 34b7e5d40e8a8f64841d126a7c8bd723cea0705e
version: 0.0.1
date-released: '2023-07-25'

GitHub Events

Total
Last Year

Dependencies

.github/workflows/ubuntu.yml actions
  • actions/cache v4 composite
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
notebooks/eqx/requirements.txt pypi
  • chex ==0.1.5
  • equinox ==0.9.2
  • jax ==0.3.25
  • matplotlib >=3.7.1
  • optax ==0.1.4
notebooks/tf/requirements.txt pypi
  • matplotlib >=3.7.1
  • tensorflow ==2.10.1
  • tensorflow-probability ==0.18.0
pyproject.toml pypi
  • equinox >=0.10.5
  • jax >=0.4.16
  • jaxlib >=0.4.16
  • jaxtyping >=0.2.20
  • optax >=0.1.7
  • tqdm >=4.66.4