News for hackers. Stuff that matters.
Re:Ask HN: What's the 'Hello World' program of neural networks? by mimo777 on Wednesday May 18, 2016 @03:32PM (#11725069)
MNIST data, which is the hand written number data. Download Tensorflow and do the examples. You will find it there.
Re:Ask HN: What's the 'Hello World' program of neural networks? by wayn3 on Thursday May 19, 2016 @08:40AM (#11729652)
Tensorflow has a whole bunch of tutorials, but those are the "Hello World"s of tensorflow, not of neural networks.

In order to get started with neural networks, begin with drawing simple neural nets for basic operations like addition, multiplication, XOR. Just represent boolean tables as neural networks.

Once you can do that, move on to implementing the algorithm yourself. A simple 3 layer network is enough to understand how the concept works. 4/2/2 nodes is plenty. Just understand how the calculations work.

Then move on to a framework - only after you understood the math. The machine learning course on coursera by Andrew Ng(?) explains the algorithms.

Re:Ask HN: What's the 'Hello World' program of neural networks? by abee1331 on Wednesday May 18, 2016 @04:32PM (#11725653)
XOR for fully connected networks, and mnist for convolutional networks
Re:Ask HN: What's the 'Hello World' program of neural networks? by argonaut on Thursday May 19, 2016 @03:11AM (#11728567)
Make sure to implement backprop yourself: don't use Tensorflow, just use numpy and write out the matrix multiplications yourself.
Re:Ask HN: What's the 'Hello World' program of neural networks? by mimo777 on Thursday May 19, 2016 @10:17AM (#11730352)
Not bad advice, but to get a feel before you dive into the deep end, use the libraries and then, by all means, follow this advice. You should always know what's underlying the functionality a library provides, but don't hesitate to start simple. I remember "C++ Neural Networks and Fuzzy Logic" at 16 and being intimidated because I had to develop and understand the code without having a background in statistics, calculus, or linear algebra. Don't let it intimidate you.
Re:Ask HN: What's the 'Hello World' program of neural networks? by argonaut on Saturday May 21, 2016 @07:19AM (#11744281)
If backprop is "the deep end," then I really don't know what you're doing...
Re:Ask HN: What's the 'Hello World' program of neural networks? by malux85 on Wednesday May 18, 2016 @04:20PM (#11725541)
Probably the XOR dataset.
Re:Ask HN: What's the 'Hello World' program of neural networks? by Wonnk13 on Thursday May 19, 2016 @08:00AM (#11729501)
Not trying to be a smartass, if "Hello, World" is the most basic program, why would a single layer perceptron model not be what OP is looking for?
Re:Ask HN: What's the 'Hello World' program of neural networks? by wayn3 on Thursday May 19, 2016 @08:36AM (#11729628)
Because that would be the equivalent of telling someone to write "Hello World" on a piece of paper in order to show them how programming works.

A single layer isn't a "neural network". The difference between logistic regression and a really simple neural network is the ability to behave in a non-linear way.

A single layer amounts to a matrix multiplication. Matrices are linear operators.

Re:Ask HN: What's the 'Hello World' program of neural networks? by billconan on Thursday May 19, 2016 @02:37PM (#11732530)
1. using a simple nn to do xor bit operation

2. mnist hand written digit recognition

Re:Ask HN: What's the 'Hello World' program of neural networks? by max_ on Thursday May 19, 2016 @03:16PM (#11732910)
XoR
Re:Ask HN: What's the 'Hello World' program of neural networks? by imakesnowflakes on Thursday May 19, 2016 @08:38AM (#11729637)
I once implemented a simple back propagation algorithm in Haskell (without any libraries) that could identify the pattern (one amoung 'A', 'B', 'C' or 'D') represented on an 8x8 matrix...

Here is the code..

https://bitbucket.org/sras/haskell-stuff/src/b58f3fc017ce303...