A guide to an efficient way to build neural network architectures- Part I --Shashank Ramesh
“If you listen to your intuition you will always know what is the best for you”
That is what is said when people give lessons on life, well it might be true for life but for training neural networks this is what i believe
“Trust your intuition but also your logic and don’t neglect one to compensate for the other”
This stems from the fact that many people i met when encountered with the question as to why did they choose certain values in their neural network architecture have generally replied saying “well just intuition and a little hit and trial”, this didn’t seem appropriate as this doesn’t help us know how efficient our model actually is and if there is any architecture combination which could help us achieve better generalized results.
So through this blog would like to share a few trips and tricks i have learnt while tinkering with deep learning models and a paved path which i follow to help me achieve the best architecture for the best results