Code Monkey home page Code Monkey logo

paper-review-continual-learning's Introduction

paper-review-continual-learning

A hub for paper reviews in Continual Learning (Lifelong Learning/Incremental Learning)

Brief overview

To start with CL, break your mind first with some notable things

CL is also frequently used interchangably with other terms

CL is sometimes misunderstood by other domains but pretty similar, refer here to distinguish.

And to evaluate a CL system, some benchmarks should be mentioned here and reinforced by V. Lomonaco here. Another benchmark to be considerd is could be refer here.

However, the gap in Continual learning is that Humans can learn a variety of concepts and skills incrementally over the course of their lives while exhibiting an array of desirable properties, such as non-forgetting, concept rehearsal, forward transfer and backward transfer of knowledge, few-shot learning, and selective forgetting. However, current methods are mostly focusing on addressing catastrophic forgetting. From that, we can argue that we have a long long way to go if we wanna achieve the real life-long learning ability.

Papers

2019

  • Learning from a Teacher using Unlabeled Data (arXiv) - review
  • Task-Free Continual Learning (CVPR2019) - review
  • Large Scale Incremental Learning (CVPR2019) - review
  • Toward Understanding Catastrophic Forgetting in Continual Learning (arxiv) - review
  • Incremental Learning Techniques for Semantic Segmentation (ICCV Workshop 2019) - review
  • Lifelong Learning Starting From Zero (AGI2019) - review
  • Continual Learning for Robotics (https://arxiv.org/abs/1907.00182) - review
  • Lifelong GAN: Continual Learning for Conditional Image Generation (arxiv) - review

2018

  • Lifelong Learning via Progressive Distillation and Retrospection (ECCV 2018) - review
  • Three scenarios for continual learning (NeurIPS Continual Learning workshop 2018) - review
  • Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines (NeurIPS Continual Learning workshop 2018) - review
  • Measuring Catastrophic Forgetting in Neural Networks (AAAI 2018) - review

2017

  • iCaRL: Incremental Classifier and Representation Learning (CVPR2017) - review
  • Overcoming Catastrophic Forgetting by Incremental Moment Matching (NIPS2017) - review
  • Continual Learning in Generative Adversarial Nets (arxiv) - review
  • Overcoming catastrophic forgetting in neural networks (EWC) (PNAS2017) - review
  • Continual Learning Through Synaptic Intelligence (ICML2017) - review

2016

  • Learning without forgetting (ECCV2016) - review

paper-review-continual-learning's People

Contributors

giangnguyen2412 avatar

Stargazers

Roman avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.