• 3 Posts
  • 5 Comments
Joined 5 months ago
cake
Cake day: February 4th, 2024

help-circle


  • I appreciate that you curate the RSS feed. I get very little time for social media these days and I’m glad there’s someone here populating feeds with content.

    I’m not a huge fan of cynicism and non-contributory comments when this space is meant to be better than the toxic sites we all fled. There’s a plethora of options for tailoring your feed to exclude unwanted content, none of which require attacking other users acting in good faith.

    Thanks to your profile, I found several new communities I will happily follow now. Keep up the good work!



  • I would ignore the people who say you should deploy a model from someone else as that will teach you next to nothing about how this stuff works.

    I would start with an older model and framework (e.g. scikitlearn) and go through all the processing, prediction, and evaluation steps using a model that’s fairly simple to understand. Since you already know about linear regression, start with some of these linear models.

    Then, and only then, would I worry about neural networks and deep learning, since the main difference is a non-linear activation function and a much more complicated set of weights (model parameters in the linear regression language).

    Here is an example

    Source: PhD in neural networks