4 Comments
User's avatar
Chetan Natesh's avatar

Very well written! Made me think about how often people jump to using tools without understanding what’s happening underneath. How do you approach deciding the number of layers and neurons in a neural network for a new problem, especially when there isn’t a clear reference point or prior work to guide the architecture?

Dr. Ashish Bamania's avatar

Hi Chetan. Thank you!

Deciding the number of layers and neurons in a neural network is a trade-off between accuracy and training compute/ inference latency. Most of this comes from trial and error.

DefiPhilosopher's avatar

This is the most concise and easy explanation on neural network training.

Though I have some questions.

Dr. Ashish Bamania's avatar

Thank you! Happy to answer them.