Details
Yes you should understand backprop
|
Andrej Karpathy on backpropagation: "The problem with Backpropagation is that it is a leaky abstraction. In other words, it is easy to fall into the trap of abstracting away the learning process — believing that you can simply stack arbitrary layers together and backprop will “magically make them work” on your data. So lets look at a few explicit examples where this is not the case in quite unintuitive ways." |
deep learning, machine learning |
Submitted by elementlist on Dec 24, 2016 |
353 views. Averaging 0 views per day. |
Please login or register if you wish to leave a comment.
Submit
New Links
Most Popular
Quick Search
Statistics
3,012 listings in 21 categories, with 2,256,914 clicks. Directory last updated Sep 12, 2023.
Welcome Amara Fatima, the newest member.
Comments on Yes you should understand backprop