Choosing filter size, strides etc. in a CNN?

Course Queries Syllabus Queries 2 years ago

0 1 0 0 0 tuteeHUB earn credit +10 pts

5 Star Rating 1 Rating

Posted on 16 Aug 2022, this text provides information on Syllabus Queries related to Course Queries. Please note that while accuracy is prioritized, the data presented might not be entirely correct or up-to-date. This information is offered for general knowledge and informational purposes only, and should not be considered as a substitute for professional advice.

Take Quiz To Earn Credits!

Turn Your Knowledge into Earnings.

tuteehub_quiz

Answers (1)

Post Answer
profilepic.png
manpreet Tuteehub forum best answer Best Answer 2 years ago

I've been looking at the CS231N lectures from Stanford and I'm trying to wrap my head around some issues in CNN architectures. What I'm trying to understand is if there are some general guidelines for picking convolution filter size and things like strides or is this more an art than a science?

Pooling I understand exists mainly to induce some form of translation invariance into a model. On the other hand, I don't have a good intuition of how stride size is picked. Are there some other guidelines to that except trying to compress the current layer size or trying to achieve a larger receptive field to a neuron? Anyone know of any good papers or similar that discuss this?

No matter what stage you're at in your education or career, TuteeHub will help you reach the next level that you're aiming for. Simply,Choose a subject/topic and get started in self-paced practice sessions to improve your knowledge and scores.