Git Product home page Git Product logo

wiki's Introduction

ContinualAI Wiki: a collaborative wiki on Continual/Lifelong Machine Learning

ContinualAI logo

The aim of the project is to create an open-source, collaborative wiki to provide a starting point for researchers, developers and AI enthusiasts who share an interest in Continual Learning and are willing to learn more or contribute to this field.
You can find info about CL workshops, media articles, companies using CL and much more.

We also provide a curated list of annotated papers in a separate repository, be sure to check it out!

Join our community on Slack to stay updated with the latest Continual Learning news.
Visit the wiki → http://wiki.continualai.org/

Below, you can find instructions on how to contribute to the wiki!


Contribute to the wiki

  • Fork the repository
  • Modify the MD files in the docs/ folder.
  • Submit a Pull Request!

About ContinualAI

ContinualAI is an open research community on the topic of Continual Learning and AI! We are a community of CL researchers and enthusiasts! Join us today on slack!

wiki's People

Contributors

andreacossu avatar biphasic avatar giparisi avatar kyloren1 avatar lrzpellegrini avatar mbiesialska avatar michaelmilstead avatar tlesort avatar vlomonaco avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

wiki's Issues

Tags to add

(from slack discussion)

Add

  • biology/experimental
  • theoretical/simulation

as tags as it might be useful to know which papers come from experimental work and which come from theoretical one.

Books in gitbook?

At the moment books are only listed in the cl-papers project and a bit hidden from the main homepage. Maybe we can add a redundant section in the wiki with selected reviews and books?

Add section discussing paradigms related to CL

In the Introduction, it would be nice to have a section in which different learning paradigms are compared.

  • Continual / Lifelong learning
  • Online Learning
  • Multi Task learning
  • Meta Learning
  • ...

This would help newcomers to put CL in the right perspective.

Research page

(from slack discussion)

Add something similar to what is listed in clair.continualai.org but an expanded and more detailed version

MongoDB dataset from Bibitex

Just a idea for the future: It would be nice to create a querable MongoDB dataset starting from the bibitex (that may be build and run in a colab notebook for example). This would allow the user to easily compute derivate stats of the continual learning letterature. For example: "how many paper has the author X produced?", "How many paper contains Continual in the title?", etc..

Allow overlapping Publication Filters

Currently papers on the publications page can be filtered by Keyword, Regex, or Date. But using any of those filters completely resets any of the others. So, you can't for example filter by keyword, then filter those down by date.

Intro: add references

(slack discussion)
add references.

  • Is there a way to link them to the research page directly ?

Add ICLR 2021 papers

Here is the list of the accepted papers.
We should add to our shared Zotero repository the papers related to CL.

Highlight link to the Github repository to contribute

Up to now the only way to discover this Github repository from the wiki is a link in the About us page.
It would be nice to highlight the link to the repository so users notice it very rapidly. Maybe by making it a button visible in every page (in the table of contents?).

Intro: remove abbreviation and keep full words.

(slack discussion)
Intro:

  • remove abbreviation and keep full words. Easier for newcomer non familiar with CL , CF ... even if a bit repetitive.
  • make an abbreviations list at the bottom of the page

Filter papers by date range

It would be nice to add a filter to the publication section where the user can filter out papers based on starting and ending year!

Improve list of benchmarks

The benchmarks are currently describe as a list. We should put together a more comprehensive and detailed view.
A table, or a more complex visualization in which, for each benchmark, we list multiple features (like CL scenario in which it can be used, type of data, possible applications and so on).

This is an example. The main problem there is to maintain updated the best accuracy. Due to the different CL scenarios available it would require a lot of effort.

Add ICLR 2020 papers

List of papers can be found here. Filter by keyword to find continual learning / lifelong learning papers.

Intro : hidden sections

(from slack discussion)

Can readthedocs be made to have hidden section by defaults which can be expanded at will ?

connected paper style relationship between papers

(from slack discussion)

Can we add something akin of connected papers to see relationships between the papers we have references here ?
Can we see clusters of CL strategies naturally arise from that ?

Add ICML 2020 papers

Here is the list of ICML 2020 papers.
Filtering by title enable to quickly look for Continual/Lifelong learning papers. Add them to the wiki.

Test GitBook

We should test whether GitBook may work as an upgrade w.r.t. sphinx and the read_the_docs template.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.