Primary competition visual

DSN AI Bootcamp Qualification Hackathon by Data Science Nigeria

Helping Nigeria
Knowledge
Completed (over 5 years ago)
Prediction
1094 joined
749 active
Starti
Sep 09, 20
Closei
Oct 03, 20
Reveali
Oct 03, 20
Parameters
Connect · 4 Oct 2020, 14:53 · edited 3 minutes later · 4

How will i know how to tune parameters... In the notebooks shared, i am seeing different parameters tuning in models we all use on a normal day, some parameters used in certain models are even looking strange to me....is there a place we can learn parameters tuning. .... you are assigning certain values to different parameters, is there any rule of thumb that guides assigning of parameters so that we don't waste time on gridsearch .

Also I will appreciate if DSN can implement a rigorous training method, the lecture given most especially the ML track which I chose is way lower than people's notebook am seeing. I will appreciate a much more authentic and rigorous training than that which we experienced with sentdex

Discussion 4 answers
User avatar
University of benin

Hmm there is no rule of thumb to that

Due to different Preprocessing and feature Engineering so you don't expect everyone to use same parameter

4 Oct 2020, 15:11
Upvotes 0
User avatar
University of benin

Try taking this course on Coursera as it helped me during the competition

How to win a data science competition on Kaggle

Watching this space to learn from others.

4 Oct 2020, 15:16
Upvotes 0