From this article, I read that "to accurately classify data with neural networks, wide layers are sometimes necessary."

However, I have seen many implementations and discussions on deep-learning, such as this, mention the concept of depth.

What is the difference in the context of neural networks? How does width vs depth impact a neural network's performance?


The width refers to the number of neurons in a layer. The depth refers to the number of layers.

Have a look at the following question regarding the impact of these hyper-parameters on the performance of the neural network: https://stats.stackexchange.com/q/214360/82135.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.