From 4e3900726be73db5abd3a6cfc6fd43b338dd1acb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=98=8A=E4=B8=80=20=E9=9B=B7?= Date: Sun, 23 Apr 2023 10:06:28 +0800 Subject: [PATCH] Add new file --- docs/components/learnware.rst | 44 +++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 docs/components/learnware.rst diff --git a/docs/components/learnware.rst b/docs/components/learnware.rst new file mode 100644 index 0000000..7fd8cf5 --- /dev/null +++ b/docs/components/learnware.rst @@ -0,0 +1,44 @@ +The Learnware Concept +===================== + +The learnware paradiam, first introduced by Zhi-Hua Zhou, is defined as a proficiently trained machine learning model accompanied by a specification that allows future users with no prior knowledge of the learnware to identify and reuse it according to their needs. + +Developers or owners of trained machine learning models can voluntarily submit their models to a learnware marketplace. If the marketplace accepts the model, it assigns a specification to the model and makes it available in the marketplace. + +Utilizing Learnware in Practice +------------------------------- + +With a learnware marketplace in place, users can tackle machine learning tasks without having to create models from scratch. + +Addressing Concerns with Learnware +---------------------------------- + +The learnware approach aims to address several challenges: + ++------------------------+----------------------------------------------------------------------------------------+ +| Concern | Solution | ++========================+========================================================================================+ +| Limited training data | Use existing high-quality learnware and require only a small amount of data for | +| | adaptation or refinement. | ++------------------------+----------------------------------------------------------------------------------------+ +| Lack of training skills| Leverage existing learnware instead of building a model from scratch. | ++------------------------+----------------------------------------------------------------------------------------+ +| Catastrophic forgetting| Retain old knowledge in the marketplace as accepted learnware remain available. | ++------------------------+----------------------------------------------------------------------------------------+ +| Continual learning | Facilitate continuous and lifelong learning with the constant influx of high-quality | +| | learnware, enriching the knowledge base. | ++------------------------+----------------------------------------------------------------------------------------+ +| Data privacy and | Ensure data privacy and proprietary protection by having developers only submit | +| proprietary concerns | models, not their data. | ++------------------------+----------------------------------------------------------------------------------------+ +| Unplanned tasks | Ensure the availability of helpful learnware for various tasks, unless entirely new | +| | to all legal developers. | ++------------------------+----------------------------------------------------------------------------------------+ +| Carbon emissions | Reduce the need to train numerous large models by assembling smaller models that | +| | provide satisfactory performance. | ++------------------------+----------------------------------------------------------------------------------------+ + +Future Work and Progress +------------------------ + +Despite the promising potential of the learnware proposal, much work remains to bring it to fruition. The following sections will discuss some of the progress made thus far.