search

COSC481W-2024Fall / MLite

A user-friendly ML platform that lets non-experts upload datasets, receive model suggestions, schedule training, and deploy models for real-time predictions
0 stars 0 forks source link

ML - Add more ML Models #30

Closed Mohammad4844 closed 2 weeks ago

Mohammad4844 commented 1 month ago

User Story:

As a user, I would like to have a wide range of models to choose from when inputting a dataset.

Persona:

Stacy the data science student would like to have a wide range of models, so that she has the ability to choose a model that will best describe her data.

Feature:

Provide a wide range of potential models for a user.

Business Value:

Users will have a wide range of potential models to select their best fit from.

Tasks

Building out a model zoo of models -- will likely be an ongoing set of issues, and has a handful of other requirements to boot. Short list of models, implemented today and intending to implement:

Acceptance Criteria

Backend python script should output an accuracy score for MLPs and SVMs that can be used to evaluate the models' fit against others, as well as a set of model weights.

Acceptance Tests

Run model api class and run the model functions.

sjiang1 commented 4 weeks ago
  1. please move your description to the first comment. You can edit the first comment by click the three dots ==> "edit"