From 2fbb6d5d3ecde3cf462724f242d5836cdd4fd241 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 14:35:41 +0800 Subject: [PATCH] Update docs/start/intro.rst --- docs/start/intro.rst | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/docs/start/intro.rst b/docs/start/intro.rst index c88edcf..383b626 100644 --- a/docs/start/intro.rst +++ b/docs/start/intro.rst @@ -53,27 +53,27 @@ Benefits of the Learnware Paradigm ---------------------------------- +-----------------------+-----------------------------------------------------------------------------------------------+ -| Benefit | Description | +| Benefit | Description | +=======================+===============================================================================================+ -| When lack of training data | Strong models can be built with small data by adapting well-performed learnwares. | +| Lack of training data | Strong models can be built with small data by adapting well-performed learnwares. | +-----------------------+-----------------------------------------------------------------------------------------------+ -| When lack of training | Ordinary users can obtain strong models by leveraging well-performed learnwares instead of | -| skills | building models from scratch. | +| Lack of training | Ordinary users can obtain strong models by leveraging well-performed learnwares instead of | +| skills | building models from scratch. | +-----------------------+-----------------------------------------------------------------------------------------------+ | Catastrophic | Accepted learnwares are always stored in the learnware market, retaining old knowledge. | | forgetting | | +-----------------------+-----------------------------------------------------------------------------------------------+ | Continual learning | The learnware market continually enriches its knowledge with constant submissions of | -| | well-performed learnwares. | +| | well-performed learnwares. | +-----------------------+-----------------------------------------------------------------------------------------------+ -| Data privacy/ | Developers only submit models, not data, preserving data privacy/proprietary. | +| Data privacy/ | Developers only submit models, not data, preserving data privacy/proprietary. | | proprietary | | +-----------------------+-----------------------------------------------------------------------------------------------+ | Unplanned tasks | Open to all legal developers, the learnware market can accommodate helpful learnwares for | -| | various tasks. | +| | various tasks. | +-----------------------+-----------------------------------------------------------------------------------------------+ | Carbon emission | Assembling small models may offer good-enough performance, reducing interest in training | -| | large models and the carbon footprint. | +| | large models and the carbon footprint. | +-----------------------+-----------------------------------------------------------------------------------------------+ Challenges and Future Work