Hi all I think there is a little risk of overfitting because we did not generate/simulate one fog pattern for each data. so it is probable that 1000 foggy sample downloaded from the internet, is only a sample of whole possible foggy states. then there is a risk of overfitting on those 1000 foggy st…

[image] saiman: just for the sake of discussion and as an example suppose in the rear-mirror example if we could guarantee (I am aware that we can not even all 10000 hours of noise car sounds similar to our ears) that one hour is a good representative of whole (real world) possible car noises, t…

Week 2/Question 10

Course Q&A Deep Learning Specialization Structuring Machine Learning Projects

manifest August 11, 2021, 2:54pm 2

Hey @saiman,

Here is a thread with a similar discussion. You may find it interesting.

Topic		Replies	Views
Data Augmentation to Address Foggy Images Quiz 2 Question 10 Structuring Machine Learning Projects coursera-platform	9	1683	November 18, 2022
Artificial data synthesis Structuring Machine Learning Projects coursera-platform	1	548	January 21, 2022
Course 3 Week 2 Miss match data Structuring Machine Learning Projects coursera-platform	2	641	January 5, 2023
W2 Test Question 10 Structuring Machine Learning Projects coursera-platform	1	562	May 31, 2022
Week2 Quiz question 10 Structuring Machine Learning Projects coursera-platform	1	663	July 21, 2021

Week 2/Question 10

Related topics