Closed K-sohooli closed 3 months ago
Name | Link |
---|---|
Latest commit | 05c7e9833036cd73f6507104ae56fd984db32da4 |
Latest deploy log | https://app.netlify.com/sites/unique-scone-f4eb67/deploys/66599e329a49d2000868ea99 |
Deploy Preview | https://deploy-preview-1135--unique-scone-f4eb67.netlify.app |
Preview on mobile | Toggle QR Code...Use your smartphone camera to open QR code link. |
To edit notification comments on pull requests, go to your Netlify site configuration.
Hello @lachlandeer , It's been a couple of months since I submitted this pull request, and I understand you may be busy with other tasks. I wanted to kindly remind you about it in case it got lost among other PRs.
Hi @K-sohooli I had a look at it - albeit not being an expert :) So one thing I found a bit funny was the paragraph "Gradient descent algorithm in simple language" that begins with "Let us consider Equation (1)" :) That is not what I would deem simple language :) For readers like me a really simple example would be great! Could you incorporate that and use it throughout the post? Thanks! A
Thanks @alexandervossen ...
@srosh2000, @shrabasteebanerjee can you also look this over and suggest any changes you have in mind?
Hello @alexandervossen, thanks for the feedback. I updated the article by including a simple example in the session "Gradient descent algorithm in simple language" to make it easier to understand. However, Gradient descent is inherently a mathematical concept. So, it contains a lot of mathematical formulas. I only mention the basic formulas which are fundamental and necessary to explain the concepts. Therefore, having a few number of formulas is unavoidable in this article. Otherwise, it is impossible to explain the concepts. I have explained in simple language how Gradient descent helps the machine learning algorithms to be optimized, and I address the important parameters in the formula that we need to tune during the optimization of an ML algorithm. Thanks for your time.
@K-sohooli I understand. But most of our methodological content is "inherently mathematical." We should nevertheless always strife to make it as accessible as possible.
For me it looks fine @srosh2000 what do you think? I would love to have a blank pull request sheet for @lachlandeer so he can enjoy his trip home :)
Looks fine to me.
Probably too technical. But something we could revist later if we looked at the ML content collectively and wanted to bring it down one level technically
Thanks @K-sohooli
This article provides an introduction to common optimization algorithms in ML. In this article, I try to explain these algorithms in a simple language and emphasize their importance in training the model. Also, the suitable optimization for each cost function is briefly mentioned. these concepts are overlooked sometimes due to their mathematics and complex appearance. so I tried to explain the basic formulas behind it very simply.