21–30 of 31 posts
The softmax_regression and logistic regression examples are even easier.
There are bindings for nodejs, python, other languages.
But it's so nice to be able to follow the definitions of each symbol and function in visual studio, not to mention being able to step through the imperative code.
And it's fast.
I kind of with people would stop using MNIST for NN tutorials. There are a billion of them already. Do something different.
Can someone explain how this repo is so popular/ why it's so popular here? This is a basic implementation of a relatively simple algorithm that you learn when initially starting with ML/DL. I do not want in any way to sound critical and am genuinely curious about the dynamics of why people would find this interesting given it's reduced complexity.
Nice. Recreating these methods in simple code for yourself is definitely the way to check you understand it. This demo looks nice, clean, and straightforward. (Although I'd rename or comment variables x and y, or give some sort of guidance on what way around the weight matrices are within the code itself.) It's also worth checking out existing neural net code-bases to see what tricks they have. The fine details usual…
'It's also worth checking out existing neural net code-bases to see what tricks they have. The fine details usually aren't in papers, and they're not all in the text-books either.' Given that you are a person who is highly-qualified to answer, I am genuinely curious why do you think that is? Reimplementing algorithms from scratch is an efficient way to learn, understand the underlying concepts and attempt improvement…
As for textbooks, I imagine that the field is moving too fast; half the stuff I use has only existed for the past year or two.
I'm seeing a lot of comments about the lack of non-MNIST neural network tutorials. Well here's mine. It uses financial data and the goal is to build a trading strategy. Its a work in progress and comments/criticism is welcome. https://github.com/LiamConnell/deep-algotrading
I kind of with people would stop using MNIST for NN tutorials. There are a billion of them already. Do something different.
Suggestions for other interesting starter projects? Doing something with NN is on the learning list...
I've started trying to get a network to recognise different vowels ("aaahhhhhh", "eeeeee", "ooooooo", etc.). Relatively easy to generate data - you just need your voice and a microphone. Downside is all the NN systems are much more set up for images than sound.
Or what about neural net fingerprint recognition. There must be databases of fingerprints somewhere. Or irises.
Recognise a type of wood from images of its grain?
Or activity recognition from accelerometer data. I think Pebble recently open sourced their recogniser and it was surprisingly not a neural network. I'm sure a neural network could do better. Might be hard to get a decent amount of data here but this could be a good incentive to do exercise!
I kind of with people would stop using MNIST for NN tutorials. There are a billion of them already. Do something different.
I found the Arrayfire examples in c++11 very approachable: https://github.com/arrayfire/arrayfire/blob/devel/examples/m... The softmax_regression and logistic regression examples are even easier. There are bindings for nodejs, python, other languages. But it's so nice to be able to follow the definitions of each symbol and function in visual studio, not to mention being able to step through the imperative code. And i…
*I work at ArrayFire.