News for hackers. Stuff that matters.

A comment on Implementing a Neural Network from Scratch in Python.

Re:Implementing a Neural Network from Scratch in Python by kowdermeister on Wednesday March 06, 2019 @01:01PM (#19321011)
I started playing around with NN-s recently and this looked like a good tutorial until the partial derivatives :) It would have been so much better to turn a complex math concept like that to code in smaller chunks because it's hard to extract from the full sample which part refers to which equation.

Also, the bias is not explained at all.

- Why is it there?

- What does it do?

- What value should it have?

[ Parent | on HN ]
Re:Implementing a Neural Network from Scratch in Python by dragandj on Wednesday March 06, 2019 @01:12PM (#19321102)
I currently publish a series of detailed articles that cover exactly that.

https://dragan.rocks/articles/19/Deep-Learning-in-Clojure-Fr...

[ Parent | on HN ]
Re:Implementing a Neural Network from Scratch in Python by victor106 on Wednesday March 06, 2019 @05:11PM (#19323414)
dragon.rocks, rocks. Your articles are some of the best i have seen on this topic. Thank you. I hope you write a book on this topic.
[ Parent | on HN ]
Re:Implementing a Neural Network from Scratch in Python by dragandj on Thursday March 07, 2019 @05:29AM (#19326962)
Thanks! We'll see. BTW, its dragAn, not dragOn :)
[ Parent | on HN ]
Re:Implementing a Neural Network from Scratch in Python by xeRTRex on Wednesday March 06, 2019 @02:35PM (#19321914)
Agreed, it is a little confusing. What makes it even more confusing is bias can be introduced as a regularization technique (to address overfitting) and these are not the same thing.

Bias in this context can be simply interpreted as analogous to the intercept in y = mx + b. Kind of like the baseline when no additional information is given.

[ Parent | on HN ]
Re:Implementing a Neural Network from Scratch in Python by applecrazy on Wednesday March 06, 2019 @06:07PM (#19323932)
Partial derivatives are basically how much a multivariate function changes based on a tiny change in a single variable. The actual math is irrelevant.
[ Parent | on HN ]