Proposal and tutorial of unstructured lifelong learning #391
Conversation
Signed-off-by: SiqiLuo <[email protected]>
Signed-off-by: SiqiLuo <[email protected]>
kubeedge-bot
added
the
size/L
kubeedge-bot
added
size/XL
docs/contributing/lib/ll_tutorial.md
Outdated
| @@ -0,0 +1,238 @@ | |||
| # How to make user-defined configuration of lifelong learning | |||
There was a problem hiding this comment.
The tutorial currently looks like a dictionary... Would be better to write it in a user-case way, i.e., considering what users would want to do, in what situation users would need certain procedures and what the procedures are.
| # Unstructured Lifelong Learning | ||
| ## Motivation | ||
|
|
||
| Edge cloud synergy lifelong learning has been proposed and realized through Sedna in [ATCII example](https://github.com/kubeedge/sedna/blob/main/examples/lifelong_learning/atcii/README.md) which handles structured data. However, the last version of Sedna lifelong learning scheme has the following limitations. |
There was a problem hiding this comment.
When talking about "However, the last version of Sedna lifelong learning scheme", would be better to specify which the mentioned version is.
There was a problem hiding this comment.
The version has been specified.
| In this version of lifelong learning, we seek to fundamentally overcome the above challenges of edge-cloud distributed machine learning. | ||
| ### Goals | ||
|
|
||
| * Supports unstructured lifelong learning. |
There was a problem hiding this comment.
It is not clear for reader to understand, like "the goal of unstructured lifelong learning is to support unstructured lifelong learning". I suggest to give a concrete explain about this goal, at least you can say "Support unstructured dataset like images"
| ## Motivation | ||
|
|
||
|
|
||
| At present, edge-cloud synergy machine learning is confronted with the challenge of heterogeneous data distributions in complex scenarios and small samples on the edge. The edge-cloud synergy lifelong learning is accordingly proposed: 1) In order to learn with shared knowledge between historical scenarios, the scheme is essentially the combination of another two learning schemes, i.e., multi-task learning and incremental learning; 2) The cloud knowledge base in lifelong learning empowers the scheme with memory ability, which helps to adapt historical knowledge to new and unseen situations on the edge. Joining the forces of multi-task learning, incremental learning and the knowledge base, the lifelong learning scheme seeks to fundamentally overcome the above challenges of edge-cloud synergy machine learning. | ||
| ### Goals |
There was a problem hiding this comment.
More details are needed
Signed-off-by: luosiqi <[email protected]> Signed-off-by: SiqiLuo <[email protected]>
Signed-off-by: SiqiLuo <[email protected]>
luosiqi
changed the title
|
/lgtm |
|
it looks good to me of the proposal, but please squash these commits to make commit history more clear, before it be merged. |
|
/lgtm |
|
/approve |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: jaypume The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
kubeedge-bot
added
the
approved
Proposal of unstructured lifelong learning and describe the following key points: