Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 3 years ago.
Improve this question
This question does not have code examples, I'm looking for an approach on how to do this.
Imagine a neural network trying to learn a game, it has 4 possible outputs (moves it can do).
In case the other player wins or gains an advantage after a (bad) move from the neural network you might want do backpropagation to teach it NOT to make this move. So you'd want to input the data [?, 0, ?, ?] to the cost function.
... but because any other move might be OK or might not be I don't have values to input for the other moves.
[1, 0, 1, 1] is not what I want.
How could you do the backpropagation on just 1 output? Does DeepLearning4J cater for this situation?
Thanks for any help!
R.
What you are looking for is called reinforcement learning. DL4J offers a solution for that with RL4J, but it isn't as well documented as it should be and supports only a few algorithms.
Related
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 9 months ago.
Improve this question
I would like to ask:
If anyone can explain the logic and architecture behind multiplayer physics-based games.
Thank you very much for your time.
During my own research about this topic, I came across these three resources and I would read them (if at all) in the following order. You will see a lot of names dropped which enable you to do further investigation:
Making Fast-Paced Multiplayer Networked Games Is Hard
UE4 networking slides
Method for simulating newtonian interactions over a computer network
In general, you will almost always have to mix several approaches to achieve the best illusion of a multi player world presence.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 5 years ago.
Improve this question
I am new to Machine Learning. I had learnt about ANN, SVR and ANN optmised with GA and PSO, but I realised that ANN involving long run time due to high computational effort. Is there any other machine learning toolbox in Matlab that perform faster than SVR?
Thanks :)
Sorry i don't know a lot on Matlab toolbox, but I can maybe help you on machine learning on a more general way. Do you need only a faster algorithm or better performing overall ?
Kind of a beginner too, but i'd say it really depends if :
it's a regression, classification or clustering task.
The complexity of the goal you want to achieve.
The Dataset you have.
I came across a microsoft post to help you chose your algorithm that is quite cool as a starting point, you should take a look, there is a graph that answers your question :
https://learn.microsoft.com/en-us/azure/machine-learning/studio/algorithm-choice
Some other will have better advices than me but heh that's a start.
Good luck,
Marc.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 4 years ago.
Improve this question
Does anyone know of an online resource where I can find stochastic matrices for an nth order Markov chain describing the probability of a note being played based on the previous n notes (for different musical genres, if possible)? I am looking for something similar to the second-order matrix found on this page: http://algorithmiccomposer.com/2010/04/openmusic-markov-chains-and-omlea.html
If not, or otherwise, what would be the best way to construct such a matrix for each genre? The article states that this can be done by hand or by analysing existing pieces of music. How could large amounts of music for each genre be processed to generate these matrices?
I have been doing research on this topic. The matrix you are looking for is highly dependant upon what kind of music you want to generate.
One of the people I work with wrote this paper that is the method used for this. It is based on using viewpoint to look at the music and then basically creating a transition matrix for all these viewpoints: http://www.ehu.es/cs-ikerbasque/conklin/papers/jnmr95.pdf
You can contact me if you need more specific info or collaboration.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 4 years ago.
Improve this question
I am new in the field of neural networks and would like to learn how to implement NNs in MATLAB. Can I have links for some step-by-step explanation of NNs using MATLAB?
It would be really helpful if applications deal with examples in Civil Engineering.
You can take a course of Andrew Ng (I believe he made most of us young people discover machine learning and become interested in this field):
https://class.coursera.org/ml-004/class
The homework includes the neural network coding by matlab.
IF you're using 2013a or later you can try typing in command window:
nnstar
They have a lot of examples with various data and different types of problems, and also after training you can have all the code you need to write the same thing on your own.
Also, you can check here the same thing, code with explanation:
Matlab Neural Network Toolbox
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 3 years ago.
Improve this question
What is the best tool for SS in CR that we can implement algorithms to see graphical result ?
Either by programming or drag&drop tools. Some I heard are Omnet++, Opnet, ns-2 (unix), Matlab. But I'm looking for lower level implementing, and less coding.
Thanks anyway.
MATLAB seems good to implement CRNs.
You can also see NS2, NS3, Omnet++.
I personally prefer Matlab.
The better tool for graphical result is MATLAB, you can also use Network Simulator-2 but it may provide you the pictorial view of node like that.
Matlab will be a good choice for implementing algorithms.
I would recommend NetSim from Tetcos for 802.22 cognitive radio simulation. You could see the following for more information
https://tetcos.com/cognitive-radio.html
https://tetcos.freshdesk.com/support/solutions/articles/14000045189-how-is-spectrum-sensing-done-in-netsim-802-22-library-