Yes you should understand backprop | by Andrej Karpathy | Medium
karpathy.medium.com · 1,627 words · saved by 14 readers
When we offered CS231n (Deep Learning class) at Stanford, we intentionally designed the programming assignments to include explicit…
Yes you should understand backprop Andrej Karpathy 7 min read · Dec 19, 2016 -- 49 Listen Share When we offered CS231n (Deep Learning class) at Stanford, we intentionally designed the programming assignments to include explicit calculations involved in backpropagation on the lowest level. The students had to implement the forward and the backward pass of each layer in raw numpy. Inevitably, some students complained on the class message boards: “Why do we have to write the backward pass when frameworks in the real world, such as TensorFlow, compute them for you automatically?” This is seemingly
saved by
- Linda
- Aryan Naik
- Adithya V
- Saeejith Nair
- Ivy Zhang
- Sherry Xie
- Marley Xiong
- Vincent Cheng
- CLL
- Liam Hinzman
- Azlen Elza
- Kevin Xu
related reading
- Neural networks and deep learningneuralnetworksanddeeplearning.com
- CS231n Deep Learning for Computer Visioncs231n.github.io
- Calculus on Computational Graphs: Backpropagation -- colah's blogcolah.github.io
- A Recipe for Training Neural Networkskarpathy.github.io
- A Recipe for Training Neural Networkskarpathy.github.io
- Backpropagation - Wikipediaen.wikipedia.org
- The Little Book of Deep Learningfleuret.org
- Backpropagation | Brilliant Math & Science Wikibrilliant.org
- What is backpropagation really doing? | 3Blue1Brown3blue1brown.com
- Neural networks and deep learningneuralnetworksanddeeplearning.com
- Vanishing gradient problem - Wikipediaen.wikipedia.org
- Don't Mess with Backprop: Doubts about Biologically Plausible Deep Learningevjang.com