Neural Network
Images are sometimes not shown due to bandwidth/network limitations. Refreshing the page usually helps.
You are currently reading a thread in /g/ - Technology
You are currently reading a thread in /g/ - Technology
Where did you guys learn Neural Network? I would like to make simple programs with FANN, but I need some materials to learn and I tought I could ask this for the best people in /g/
pic related
how much computation power does it take to make a simple neural network that actually does something cool?
>>52529929
Define cool.
>>52529954
waifu2x is pretty cool
Touch (Lua) is a good library to learn AI?
>>52529864
I did:
1)
>>52529907
+Pretty okay
- Hardly any good PDF available
- Really long
+ It's the authoritative book on AI
+ Best notation
2)
http://neuralnetworksanddeeplearning.com/
+ Pretty short and to the point
+ Requires leat math/probability knowledge
+/- Its python
- Total basics
- Notation is a bit shit
3)
Murphy's "Machine Learning: A Probabilistic Perspective" is pretty okay but you'll need to know your maths pretty well.
4)
Barber's "Bayesian Reasoning and Machine Learning" is a bit less math and nice as well. Plus it's an officially free book and has matlab code. It has the NN part kind of 'mixed in' with the rest though, so not great if you ONLY want to learn nn (which I wouldnt advise but well)
Anyway consider:
- There is no accepted notation around the field so there is like a compatibility problem between any two books/websites/wikipedia etc
- R&N's is the industry standard
This is not the 90's.
There are better alternatives to neural networks.
The concept of neural networks is not that complicated but the problem is that you cannot really explain what the model represents.
This makes the whole model worthless.
>>52530295
thx anon, i will start soon with IA too.
You can learn and implement a basic nnet in Andrew Ng's intro to machine learning course on coursera, which is free and available anytime.
NNETs are certainly not useless and are used in industry all the time for image recognition and similar tasks. FB, google, etc. all use deep nets.
>>52530446
We can't explain how our brains work either, but they aren't worthless.
>>52530674
How can you create something if you don't know where to start?
>>52530295
I haven't looked at Murphys book in a while but from what I remember the book seemed to mainly focus on Bayes nets?
>>52530038
You won't be making a waifu out of NN
>>52530674
I believe it is more beneficial to replicate the brain by replicating the behaviors rather than mimicking the construction.
>>52530715
You do know where to start. You start by developing a neural network and train it for the task.
>>52530674
i once feeled clever being able to do neural nets, but once you realize no one can explain WHY it actually works, you finally understand it's just about implementing a basic algorithm, with some math you don't even understand anyway, (code monkey really)
>>52530772
The thing is that the brain is far too complex to simulate using traditional methods. Neural networks is the only way we know that even comes close. There is likely a reason the brain evolved using the architecture it does.
>>52530827
Give one example where ANN is a good method, classification? decision making? we have better better methods to do those things.
If we should mimic the behaviors of the brain, we should focus on signal processing rather than ANN.
>>52530900
This.
ANN are overrated.
They are power hungry tools you use when you have no idea how to solve a problem.
>>52530772
>replicating the behaviors rather than mimicking the construction.
But the construction of the brain ENABLES the behaviors to happen, You can make normal computers replicate behaviors because you know what you want it to do, but if you just provide the groundwork you get something unique
>>52529929
It's not going to do "something cool" just by itself.
It's not magic, it's just mathematics.
You can use neural networks for specific tasks like pattern recognition or separating data into groups.
>>52531088
as I said.
Welcome to the 90's.
Say I contract you to build me a system that could manage peoples taxes with a neural network.
In the beginning everything would be controlled by humans and over time, the system would be powerful enough to handle everything.
Would that be a good system?
Would that be a good way to design such a system?
>>52531663
>Say I contract you to build me a system that could manage peoples taxes with a neural network.
how is that a task more suitable for neural networks than an algorithmic program?
in highschool
it was a meme
proof op is underaged and thinks neural nets are a real thing top kek
>>52529929
search for Nvidia DIGITS Devbox.
And that's like a "starting point"..
>>52531796
It is not.
That is my point.
In the 90's people thought everything could be solved by ANN.
Because human brains can solve any problem, ANN would be the solution to replace humans without having to specify anything more than the data and the desired outcome.
Nobody thinks that way anymore.
>>52531959
>hurr use it for everything
>durr you can't therefore it has no use at all
>>52532078
What about situations where it could be applied?
Classification? depending on the data, there is simpler methods, there is better methods and there is faster methods. Random forest is a lot better if the data is complex.
Decision making? Maybe, but again making a model based on knowledge of the task is usually better. Monte Carlo would be more efficient for most games.
https://youtube.com/watch?v=qv6UVOQ0F44
