Merge pull request #1 from neurodata/main

Pulling new changes
david-z-shi · Oct 25, 2020 · e6ab8db · e6ab8db
2 parents 4faa8e2 + 9ee05b7
commit e6ab8db
Show file tree

Hide file tree

Showing 110 changed files with 3,443 additions and 4,979 deletions.
diff --git a/.github/ISSUE_TEMPLATE/bug_report.md b/.github/ISSUE_TEMPLATE/bug_report.md
@@ -1,6 +1,6 @@
 ---
 name: Bug Report
-about: Create a report to help us improve hyppo
+about: Create a report to help us improve ProgLearn
 label: bug
 
 ---

diff --git a/.github/ISSUE_TEMPLATE/documentation_fix.md b/.github/ISSUE_TEMPLATE/documentation_fix.md
@@ -1,6 +1,6 @@
 ---
 name: Documentation Fix
-about: Create a report to help us improve the documentation of hyppo
+about: Create a report to help us improve the documentation of ProgLearn
 label: documentation
 
 ---

diff --git a/.github/ISSUE_TEMPLATE/feature_request.md b/.github/ISSUE_TEMPLATE/feature_request.md
@@ -1,6 +1,6 @@
 ---
 name: Feature Request
-about: Suggest an idea for hyppo
+about: Suggest an idea for ProgLearn
 label: enhancement
 
 ---

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -4,25 +4,35 @@ Contributing to ProgLearn
 (adopted from scikit-learn)
 
 The latest contributing guide is available in the repository at
-`docs/contributing.rst`
+`docs/contributing.rst`, or online at:
+
+[https://proglearn.neurodata.io/contributing.html](https://proglearn.neurodata.io/contributing.html)
+
 
 There are many ways to contribute to ProgLearn, with the most common ones
 being contribution of code or documentation to the project. Improving the
 documentation is no less important than improving the library itself. If you
 find a typo in the documentation, or have made improvements, do not hesitate to
 submit a GitHub pull request. Documentation can be found under the
-[docs/](https://github.com/neurodata/progressive-learning/tree/master/docs) directory.
+[docs/](https://github.com/neurodata/ProgLearn/tree/main/docs) directory.
 
 But there are many other ways to help. In particular answering queries on the
-[issue tracker](https://github.com/neurodata/progressive-learning/issues), and
-investigating bugs are very valuable contributions that decrease the burden on 
+[issue tracker](https://github.com/neurodata/ProgLearn/issues), and
+investigating bugs are very valuable contributions that decrease the burden on
 the project maintainers.
 
 Another way to contribute is to report issues you're facing, and give a "thumbs
 up" on issues that others reported and that are relevant to you. It also helps
 us if you spread the word: reference the project from your blog and articles,
 link to it from your website, or simply star it in GitHub to say "I use it".
 
+Quick links
+-----------
+
+* [Submitting a bug report or feature request](http://proglearn.neurodata.io/contributing.html#submitting-a-bug-report-or-a-feature-request)
+* [Contributing code](http://proglearn.neurodata.io/contributing.html#contributing-code)
+* [Coding guidelines](http://proglearn.neurodata.io/contributing.html#coding-guidelines)
+
 Code of Conduct
 ---------------
 

diff --git a/README.md b/README.md
@@ -1,80 +1,21 @@
 # ProgLearn
 
-[![Build Status](https://travis-ci.org/neurodata/progressive-learning.svg?branch=master)](https://travis-ci.org/neurodata/progressive-learning)
-[![codecov](https://codecov.io/gh/neurodata/progressive-learning/branch/master/graph/badge.svg)](https://codecov.io/gh/neurodata/progressive-learning)
+[![Build Status](https://travis-ci.org/neurodata/ProgLearn.svg?branch=main)](https://travis-ci.org/neurodata/ProgLearn)
+[![codecov](https://codecov.io/gh/neurodata/ProgLearn/branches/main/graph/badge.svg)](https://codecov.io/gh/neurodata/ProgLearn)
 [![PyPI version](https://img.shields.io/pypi/v/proglearn.svg)](https://pypi.org/project/proglearn/)
 [![arXiv shield](https://img.shields.io/badge/arXiv-2004.12908-red.svg?style=flat)](https://arxiv.org/abs/2004.12908)
 [![License](https://img.shields.io/badge/License-MIT-blue)](https://opensource.org/licenses/MIT)
 
-`proglearn` (**Prog**ressive **Learn**ing) is a package for exploring and using progressive learning algorithms developed by the [neurodata group](https://neurodata.io).
+`ProgLearn` (**Prog**ressive **Learn**ing) is a package for exploring and using progressive learning algorithms developed by the [neurodata group](https://neurodata.io).
 
-- [Overview](#overview)
-- [Documentation](#documentation)
-- [System Requirements](#system-requirements)
-- [Installation Guide](#installation-guide)
-- [Contributing](#contributing)
-- [License](#license)
-- [Issues](#issues)
+- **Installation Guide:** [http://proglearn.neurodata.io/install.html](http://proglearn.neurodata.io/install.html)
+- **Documentation:** [http://proglearn.neurodata.io](http://proglearn.neurodata.io)
+- **Tutorials:** [http://proglearn.neurodata.io/tutorials.html](http://proglearn.neurodata.io/tutorials.html)
+- **Source Code:** [http://proglearn.neurodata.io/reference/index.html](http://proglearn.neurodata.io/reference/index.html)
+- **Issues:** [https://github.com/neurodata/proglearn/issues](https://github.com/neurodata/proglearn/issues)
+- **Contribution Guide:** [http://proglearn.neurodata.io/contributing.html](http://proglearn.neurodata.io/contributing.html)
 
-# Overview
-The natural process of biological learning involves progressive acquisition of new information developing on past knowledge and experiences, which often leads to a performance improvement on a given task. Learning a second language, for instance, is associated with higher performance in an individual’s native language compared to that of monolinguals. In classical machine learning, the process usually begins from the state of <i>tabula rasa</i>, zero knowledge, and is optimized for a single task. The issues arise when the system is sequentially optimized for multiple tasks exhibiting “catastrophic forgetting,” diminishing performance of previously learned tasks. One of the current limitations of artificial intelligence revolves around this inability to transfer knowledge. <br><br>
-The progressive learning package utilizes representation ensembling algorithms to sequentially learn a representation for each task and ensemble both old and new representations for all future decisions. Here, two complementary representation ensembling algorithms based on decision forests (Lifelong Forest) and deep networks (Lifelong Network) demonstrate forward and backward knowledge transfer of tasks on multiple real datasets, including both vision and language applications.
-
-# Documentation
-
-
-# System Requirements
-## Hardware requirements
-`proglearn` package requires only a standard computer with enough RAM to support the in-memory operations. 
-
-## Software requirements
-### OS Requirements
-This package is supported for *Linux* and *macOS*. The package has been tested on the following systems:
-+ Linux: Ubuntu 16.04
-+ macOS: Mojave (10.14.1)
-+ Windows: 10 
-
-### Python Requirements
-This package is written for Python3. Currently, it is supported for Python 3.6 and 3.7.
-
-### Python Dependencies
-`proglearn` mainly depends on the Python scientific stack.
-```
-keras>=2.3.1
-tensorflow>=1.19.0
-scikit-learn>=0.22.0
-scipy==1.4.1
-numpy<1.19
-joblib>=0.14.1
-``` 
-
-# Installation Guide
-## Install from pip
-```
-pip install proglearn
-```
-
-## Install from Github
-```
-git clone https://github.com/neurodata/progressive-learning.git
-cd progressive-learning
-python3 setup.py install
-```
-
-# Contributing
-We welcome contributions from anyone. Please see our [contribution guidelines](https://github.com/neurodata/progressive-learning/blob/master/CONTRIBUTING.md) before making a pull request. Our 
-[issues](https://github.com/neurodata/progressive-learning/issues) page is full of places we could use help! 
-If you have an idea for an improvement not listed there, please 
-[make an issue](https://github.com/neurodata/progressive-learning/issues/new) first so you can discuss with the 
-developers. 
-
-# License
-This project is covered under the [MIT License](hhttps://github.com/neurodata/progressive-learning/blob/master/LICENSE).
-
-# Issues
-We appreciate detailed bug reports and feature requests (though we appreciate pull requests even more!). Please visit our [issues](https://github.com/neurodata/progressive-learning/issues) page if you have questions or ideas.
-
-# Citing progressive-learning
-If you find progressive-learning useful in your work, please cite the package via the [progressive-learning paper](https://arxiv.org/pdf/2004.12908.pdf)
-
-> Vogelstein JT, Helm HS, Mehta RD, Dey J, Yang W, Tower B, LeVine W, Larson J, White C, Priebe CE. A general approach to progressive learning. arXiv preprint arXiv:2004.12908. 2020 Apr 27.
+Some system/package requirements:
+- **Python**: 3.6+
+- **OS**: All major platforms (Linux, macOS, Windows)
+- **Dependencies**: keras, scikit-learn, scipy, numpy, joblib
diff --git a/experiments/cifar_exp/appendix_tables.ipynb → benchmarks/cifar_exp/appendix_tables.ipynb b/experiments/cifar_exp/appendix_tables.ipynb → benchmarks/cifar_exp/appendix_tables.ipynb
diff --git a/...far_exp/benchmarking_pickle_conversion.py → ...far_exp/benchmarking_pickle_conversion.py b/...far_exp/benchmarking_pickle_conversion.py → ...far_exp/benchmarking_pickle_conversion.py
diff --git a/...far_exp/experiment_varying_task_sample.py → ...far_exp/experiment_varying_task_sample.py b/...far_exp/experiment_varying_task_sample.py → ...far_exp/experiment_varying_task_sample.py
diff --git a/experiments/cifar_exp/fte_bte_exp.py → benchmarks/cifar_exp/fte_bte_exp.py b/experiments/cifar_exp/fte_bte_exp.py → benchmarks/cifar_exp/fte_bte_exp.py
diff --git a/experiments/cifar_exp/plot_cifar_all_algo.py → benchmarks/cifar_exp/plot_cifar_all_algo.py b/experiments/cifar_exp/plot_cifar_all_algo.py → benchmarks/cifar_exp/plot_cifar_all_algo.py
diff --git a/experiments/cifar_exp/plot_one_algo.py → benchmarks/cifar_exp/plot_one_algo.py b/experiments/cifar_exp/plot_one_algo.py → benchmarks/cifar_exp/plot_one_algo.py
diff --git a/experiments/cifar_exp/plot_time_space.py → benchmarks/cifar_exp/plot_time_space.py b/experiments/cifar_exp/plot_time_space.py → benchmarks/cifar_exp/plot_time_space.py
diff --git a/...ments/cifar_exp/result/figs/benchmark.pdf → ...marks/cifar_exp/result/figs/benchmark.pdf b/...ments/cifar_exp/result/figs/benchmark.pdf → ...marks/cifar_exp/result/figs/benchmark.pdf
diff --git a/...cifar_exp/result/figs/fig_trees20__uf.pdf → ...cifar_exp/result/figs/fig_trees20__uf.pdf b/...cifar_exp/result/figs/fig_trees20__uf.pdf → ...cifar_exp/result/figs/fig_trees20__uf.pdf
diff --git a/...cifar_exp/result/figs/fig_trees30__uf.pdf → ...cifar_exp/result/figs/fig_trees30__uf.pdf b/...cifar_exp/result/figs/fig_trees30__uf.pdf → ...cifar_exp/result/figs/fig_trees30__uf.pdf
diff --git a/...cifar_exp/result/figs/fig_trees40__uf.pdf → ...cifar_exp/result/figs/fig_trees40__uf.pdf b/...cifar_exp/result/figs/fig_trees40__uf.pdf → ...cifar_exp/result/figs/fig_trees40__uf.pdf
diff --git a/...cifar_exp/result/figs/fig_trees50__uf.pdf → ...cifar_exp/result/figs/fig_trees50__uf.pdf b/...cifar_exp/result/figs/fig_trees50__uf.pdf → ...cifar_exp/result/figs/fig_trees50__uf.pdf
diff --git a/...exp/result/figs/space_time_efficiency.pdf → ...exp/result/figs/space_time_efficiency.pdf b/...exp/result/figs/space_time_efficiency.pdf → ...exp/result/figs/space_time_efficiency.pdf
diff --git a/...xp/result/figs/space_time_efficiency2.pdf → ...xp/result/figs/space_time_efficiency2.pdf b/...xp/result/figs/space_time_efficiency2.pdf → ...xp/result/figs/space_time_efficiency2.pdf
diff --git a/...ult/result/figs/fig_fixed_trees10__uf.pdf → ...ult/result/figs/fig_fixed_trees10__uf.pdf b/...ult/result/figs/fig_fixed_trees10__uf.pdf → ...ult/result/figs/fig_fixed_trees10__uf.pdf
diff --git a/...ult/result/figs/fig_fixed_trees20__uf.pdf → ...ult/result/figs/fig_fixed_trees20__uf.pdf b/...ult/result/figs/fig_fixed_trees20__uf.pdf → ...ult/result/figs/fig_fixed_trees20__uf.pdf
diff --git a/...ult/result/figs/fig_fixed_trees30__uf.pdf → ...ult/result/figs/fig_fixed_trees30__uf.pdf b/...ult/result/figs/fig_fixed_trees30__uf.pdf → ...ult/result/figs/fig_fixed_trees30__uf.pdf
diff --git a/...ult/result/figs/fig_fixed_trees40__uf.pdf → ...ult/result/figs/fig_fixed_trees40__uf.pdf b/...ult/result/figs/fig_fixed_trees40__uf.pdf → ...ult/result/figs/fig_fixed_trees40__uf.pdf
diff --git a/...ult/result/figs/fig_fixed_trees50__uf.pdf → ...ult/result/figs/fig_fixed_trees50__uf.pdf b/...ult/result/figs/fig_fixed_trees50__uf.pdf → ...ult/result/figs/fig_fixed_trees50__uf.pdf
diff --git a/...xp/result/result/figs/fig_trees0__dnn.pdf → ...xp/result/result/figs/fig_trees0__dnn.pdf b/...xp/result/result/figs/fig_trees0__dnn.pdf → ...xp/result/result/figs/fig_trees0__dnn.pdf
diff --git a/...xp/result/result/figs/fig_trees10__uf.pdf → ...xp/result/result/figs/fig_trees10__uf.pdf b/...xp/result/result/figs/fig_trees10__uf.pdf → ...xp/result/result/figs/fig_trees10__uf.pdf
diff --git a/...xp/result/result/figs/fig_trees20__uf.pdf → ...xp/result/result/figs/fig_trees20__uf.pdf b/...xp/result/result/figs/fig_trees20__uf.pdf → ...xp/result/result/figs/fig_trees20__uf.pdf
diff --git a/...xp/result/result/figs/fig_trees30__uf.pdf → ...xp/result/result/figs/fig_trees30__uf.pdf b/...xp/result/result/figs/fig_trees30__uf.pdf → ...xp/result/result/figs/fig_trees30__uf.pdf
diff --git a/...xp/result/result/figs/fig_trees40__uf.pdf → ...xp/result/result/figs/fig_trees40__uf.pdf b/...xp/result/result/figs/fig_trees40__uf.pdf → ...xp/result/result/figs/fig_trees40__uf.pdf
diff --git a/...xp/result/result/figs/fig_trees50__uf.pdf → ...xp/result/result/figs/fig_trees50__uf.pdf b/...xp/result/result/figs/fig_trees50__uf.pdf → ...xp/result/result/figs/fig_trees50__uf.pdf
diff --git a/...iments/label_shuffle/label_shuffle_exp.py → ...hmarks/label_shuffle/label_shuffle_exp.py b/...iments/label_shuffle/label_shuffle_exp.py → ...hmarks/label_shuffle/label_shuffle_exp.py
diff --git a/experiments/label_shuffle/plot_cifar.py → benchmarks/label_shuffle/plot_cifar.py b/experiments/label_shuffle/plot_cifar.py → benchmarks/label_shuffle/plot_cifar.py
diff --git a/...l_shuffle/result/figs/fig_trees0__dnn.pdf → ...l_shuffle/result/figs/fig_trees0__dnn.pdf b/...l_shuffle/result/figs/fig_trees0__dnn.pdf → ...l_shuffle/result/figs/fig_trees0__dnn.pdf
diff --git a/...l_shuffle/result/figs/fig_trees10__uf.pdf → ...l_shuffle/result/figs/fig_trees10__uf.pdf b/...l_shuffle/result/figs/fig_trees10__uf.pdf → ...l_shuffle/result/figs/fig_trees10__uf.pdf
diff --git a/...l_shuffle/result/figs/fig_trees20__uf.pdf → ...l_shuffle/result/figs/fig_trees20__uf.pdf b/...l_shuffle/result/figs/fig_trees20__uf.pdf → ...l_shuffle/result/figs/fig_trees20__uf.pdf
diff --git a/...l_shuffle/result/figs/fig_trees30__uf.pdf → ...l_shuffle/result/figs/fig_trees30__uf.pdf b/...l_shuffle/result/figs/fig_trees30__uf.pdf → ...l_shuffle/result/figs/fig_trees30__uf.pdf
diff --git a/...l_shuffle/result/figs/fig_trees40__uf.pdf → ...l_shuffle/result/figs/fig_trees40__uf.pdf b/...l_shuffle/result/figs/fig_trees40__uf.pdf → ...l_shuffle/result/figs/fig_trees40__uf.pdf
diff --git a/...l_shuffle/result/figs/fig_trees50__uf.pdf → ...l_shuffle/result/figs/fig_trees50__uf.pdf b/...l_shuffle/result/figs/fig_trees50__uf.pdf → ...l_shuffle/result/figs/fig_trees50__uf.pdf
diff --git a/...el_shuffle/result/figs/label_shufffle.pdf → ...el_shuffle/result/figs/label_shufffle.pdf b/...el_shuffle/result/figs/label_shufffle.pdf → ...el_shuffle/result/figs/label_shufffle.pdf
diff --git a/...iments/parity_experiment/experiment.ipynb → ...hmarks/parity_experiment/experiment.ipynb b/...iments/parity_experiment/experiment.ipynb → ...hmarks/parity_experiment/experiment.ipynb