-
Notifications
You must be signed in to change notification settings - Fork 425
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
f3dfe13
commit a96b448
Showing
1 changed file
with
28 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,28 @@ | ||
# Assignment Proposal | ||
|
||
## Title | ||
|
||
Using Comet ML to analyze and compare the performance of ML models | ||
|
||
## Names and KTH ID | ||
|
||
- Lauren Llauradó ([email protected]) | ||
- Pere Mateu Raventós ([email protected]) | ||
|
||
## Deadline | ||
|
||
- Week 4 | ||
|
||
## Category | ||
|
||
- Demo | ||
|
||
## Description | ||
|
||
The objective of this demonstration is to show the importance of having a way to test and compare the performance of ML models for our applications. | ||
|
||
To do that, we will create two simple machine learning models with a simple dataset, and see that the performance analysis is not a straightforward task, due to having many metrics and ways to analyze it, and each one having its own libraries and structure. Then, we will use Comet ML, which has all the metrics integrated in one single place. Then we will also show how it makes it easy to use them in different applications. | ||
|
||
**Relevance** | ||
|
||
Being able to easily analyze the performance of your models is crucial, in order to accelerate the model iterations. In addition, comparing models and being able to reproduce tests in multiple scenarios also lets you be consistent and go faster in your machine learning projects. |