Choosing a neural network architecture for Snake AI Agent [closed] - machine-learning

Closed. This question is not about programming or software development. It is not currently accepting answers.
This question does not appear to be about a specific programming problem, a software algorithm, or software tools primarily used by programmers. If you believe the question would be on-topic on another Stack Exchange site, you can leave a comment to explain where the question may be able to be answered.
Closed 5 months ago.
Improve this question
I'm new to machine learning and reinforcement learning, and I'm attempting to create an AI agent that learns to play Snake. I am having trouble choosing / developing a neural network architecture that can work with the shape of my input / output vectors.
My input is a 3x10x10 tensor, basically 3 layers of a 10x10 grid the snake moves on
(I only use 0s and 1s throughout the tensor, mark the position of the snake's body parts
in the first layer, mark the apple's position on the second layer, and the snake's head position on the 3rd).
For my output, I'm looking for a vector of 4 values, corresponding to the 4 possible moves a player has available (change direction to up / down / left / right).
I would appreciate any recommendations on how to go about choosing an architecture in this case, as well as any thoughts regarding the way I chose to encode my game state into an input vector for the agent to train.

You could maybe use a ResNet architecture at the beginning and see what happens. Basically, the ResNet takes as input an image of a shape HxWxC, where H-height, W-width, C-channels. In your case, you do not have an actual image, but you still encode your environment in 3 channels, with a HxW=10x10. So, I think your encoding should work.
Then you will also have to change the output of the ResNet so that you will only output 4 values and each value will correspond to one action.
Given that the input space is not that big, maybe you could start with a ResNet 18 which is very small and see what happens. Given that you are new to ML and RL, there is a very old paper that tries to solve Atari games using deep learning https://arxiv.org/pdf/1312.5602v1.pdf and the method is not that hard to understand. Snake is a game with a similar (or even less) complexity as Atari games, so this paper may provide more insights.

Related

What type of neural network would work best for credit scoring? [closed]

Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 4 years ago.
Improve this question
Let me just start by saying I only took the undergrad AI class at school so I know just enough to be dangerous.
Here's the problem I'm looking to solve...accurate credit scoring is a key part to the success of my business. Currently we rely on a team of actuaries and statistical analysis to suss out patterns in the few dozen variables we track about each individual that indicate that they may be a low or high credit risk. As I understand it this is exactly the type of job that neural nets are great at solving, that is, finding high order relationships across many inputs that a human would likely never spot and then rendering a decision or output that is on average more accurate than what a trained human could do. In short, I want to be able to input your name, address, marital status, what car you drive, where you work, hair color, favorite food, etc in and get a credit score back.
My question is what type or architecture for a neural network would be best for this particular problem. I've done a bit of research and it seems I'm generating questions faster than I'm finding answers at this point. The best I've been able to come up with is some kind of generative deep neural network with multiple hidden layers where each layer is able to abstract one level beyond the previous one. Im assuming it's going to be feed-forward just because it seems to be the default. We have historical data on all previous customers including the information we used to make the initial score as well as data on what type of credit risk they actually turned out to be. This would seem to lend itself to unsupervised learning. Where I'm lost is in number of layers, how the layers are different from each other, size of each layer, connectedness of each of the perceptrons and so on. The more I dig the more I'm getting into research papers that are over my head so I just need some smart person to point me in the right direction
Does anyone have any ideas? Again, I don't need a thorough explanation just a general area I should focus on.
This is supervised learning since you have actual data that can be labelled. It's also feedforward since you're not predicting time series but assigning scores. Further, you should probably just prepare your data (assigning credit scores manually or with some rough heuristic) and start experimenting with some tools before you invest time into implementing state-of-the-art architectures. A multi-layer-perceptron (MLP) with 1 hidden layer is a sufficient starting point for such a problem. From there on, you can train the network to generalize your credit assignment heuristic you began with.
You should know that most "new" architectures you probably read about while researching are dealing with much more difficult problems than credit scoring (speech/image/character recognition/detection). There is a collection of papers on the scenario of credit scoring / risk classification, so I'd recommend reshifting your focus from architectures to actual case studies (see e.g. this paper). Just pick a recent paper with MLPs and apply their parameters. Start simple and improve the system incrementally (as #roganjosh stated).

Automatic flora detection in Images [closed]

Closed. This question is off-topic. It is not currently accepting answers.
Want to improve this question? Update the question so it's on-topic for Stack Overflow.
Closed 10 years ago.
Improve this question
My image dataset is from http://www.image-net.org. There are various synsets for different things like flora, fauna, persons, etc
I have to train a classifier which predicts 1 if the image belongs to floral synset and 0, otherwise.
Images belonging to floral synset can be viewed at http://www.image-net.org/explore, by clicking on the plant, flora, plant life option in the left pane.
These images include wide variety of flora - like trees, herbs, shrubs, flowers etc.
I am not able to figure out what features to use to train the classifier. There is a lot of greenery in these images, but there are many flower images, which don't have much green component. Another feature is the shape of the leaves and the petals.
It would be helpful if anyone could suggest how to extract this shape feature and use it to train the classifier. Also suggest what other features could be used to train the classifier.
And after extracting features, which algorithm is to be used to train the classifier?
Not sure that shape information is the approach for the data set you have linked to.
Just having a quick glance at some of the images I have a few suggestions for classification:
Natural scenes rarely have straight lines - Line detection
You can discount scenes which have swathes of "unnatural" colour in them.
If you want to try something more advanced I would suggest that a hybrid between entropy/pattern recognition would form a good classifier as natural scenes have alot of both.
Attempting template-matching/shape matching for leaves/petals will break your heart - you need to use something much more generalised.
As for which classifier to use... I'd normally advise K-means initially and once you have some results determine if the extra effort to implement Bayes or a Neural Net would be worth it.
Hope this helps.
T.
Expanded:
"Unnatural Colors" could be highly saturated colours outside of the realms of greens and browns. They are good for detecting nature scenes as there should be ~50% of the scene in the green/brown spectrum even if a flower is at the center of it.
Additionally straight line detection should yield few results in nature scenes as straight edges are rare in nature. On a basic level generate an edge image, Threshold it and then search for line segments (pixels which approximate a straight line).
Entropy requires some Machine Vision knowledge. You would approach the scene by determining localised entropys and then histogramming the results here is a similar approach that you will have to use.
You would want to be advanced at Machine Vision if you are to attempt pattern recognition as this is a difficult subject and not something you can throw up in code sample. I would only attempt to implement these as a classifier once colour and edge information(lines) has been exhausted.
If this is a commercial application then a MV expert should be consulted. If this is a college assignment (unless it is a thesis) colour and edge/line information should be more than enough.
HOOG features are pretty much the de-facto standard for these kinds of problems, I think. They're a bit involved to compute (and I don't know what environment you're working in) but powerful.
A simpler solution which might get you up and running, depending on how hard the dataset is, is to extract all overlapping patches from the images, cluster them using k-means (or whatever you like), and then represent an image as a distribution over this set of quantised image patches for a supervised classifier like an SVM. You'd be surprised how often something like this works, and it should at least provide a competitive baseline.

Neural network: should the algorithm be rewritten for every case? [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I have 2 sequences of numbers and I'd want to continue it using neural algorithms (there is some logic in them, but I don't know what, and there are no external factors affecting the selection). There are some relationship is in each of the two sequences separately, as well as between them.
So, I'm new to machine learning, but I've got such an idea: is there any already written-and-well-working applications (libraries) that implement exact algorithms for me not to learn them all before using. Simply like "most-frequently-used-neural-algorithms-kit".
I'm thinking of analysing some music sheets and two sequences: "notes" and "durations".
OK, according to the comments I think I got what you want.
Generally, no, you don't need to rewrite the standard algorithm of ANN. But be aware that ANN is not an algorithm, but a cluster of algorithms (including BackPropagation-ANN, Hopfield-ANN, Boltzmann Machine etc). Among them I recommend BP-ANN which is simple and suitable for your project. You might want to input a sequences of the known notes and duration, and then expect an output of the next note and duration.
To use BP-ANN, you don't need to rewrite them. Due to its a widely-used algorithm, there are many toolkits and open source implementations of it:
Google "back propagation neural network implementation", you will find it easily. There are also a few opensource projects on Github(in both C language and Matlab): https://github.com/search?q=back+propagation&type=Everything&repo=&langOverride=&start_value=1
For further reading if you also want to deeply understand the details of its implementation, read this: http://docs.lib.purdue.edu/cgi/viewcontent.cgi?article=1279&context=ecetr&sei-redir=1
If you're interested in neural networks there are plenty of libraries available.
ANNIE is one such open source example, the MATLAB Neural Network toolbox is a
commercial example. These are libraries which you tell the architecture of the
neural network, you can train, test, verify, etc. The important part in all
these machine learning methods is how you represent your data, and those were
the comments you were getting (for example Predictor's). Sometimes you get
excellent results with one representation and very bad results with others.
There are also libraries to train SVMs (a specialized algorithm to train neural
networks) with quadratic regularization, LIBSVM is one great example.
There is also plenty of work on predicting time series with neural networks (if
that is what you want to do with music, I am not sure what exactly you want).
If the input is a series of (note, duration) pairs, then I suspect you'd get much farther by summarizing the historical note-to-note transitions or by something similar in an effort to capture the syntax of the music (Markov analysis, etc.), than you would by stuffing this into a neural network. It may help, too, to try representing the series as note differentials, measuring how many notes up or down the scale the new note is, rather than the actual value of the note itself.

How to implement an artificial neural network in Delphi? [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I want to have an artificial neural network:
42 input neurons
168 hidden neurons
7 output neurons
This network is to play the game of "Connect Four". At the end of each game, the network gets feedback (game result / win?).
Learning should be done with Temporal Difference Learning.
My questions:
What values should be in my reward array?
And finally: How can I apply it to my game now?
Thank you so much in advance!
First hit is: you're assigning '0' to t in 'main', but your arrays' low-bound is '1', so you're accessing a non-existing element in the loops, hence the AV.
If you had enabled range-checking in compiler options, you'd be getting a range check error and you probably would have find the reason earlier.
BTW, since I have no idea what the code is doing, I wouldn't possibly notice any other errors at this time..
If you're interested in using a third party library (free for non-commercial products, I've been very happy with some tools from this company http://www.mitov.com/html/intelligencelab.html (although I've never used their intelligence lab, just video tools.)
Fast Artificial Neural Network (FANN) is a good open source library, its been optimised and used by a large community, with plenty of support and delphi bindings.
Using dependencies in this area is advised if you don't fully understand what your doing, the smallest detail can have a big impact on how a neural network performs; so best spend your time on your implementation of the network, then on anything else.
Other links that may be helpful for you:
http://delphimagic.blogspot.com.ar/2012/12/red-neuronal-backpropagation.html
(Includes source code)
Coding a Backpropagation neural network with two input neurons, two output and one hidden layer.
The sample provides two sets of data that can train the network and see how accurate learning minimizing the error shown in a graph.
Modifying the program can change the number of times the network trained with test data (epochs)

Pitch detection using neural networks [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I am trying to use ANN for pitch detection of musical notes. The network is a simple two-layer MLP, whose inputs are basically a DFT (averaged and logarithmically distributed), and 12 outputs correspond to the 12 notes of a particular octave.
The network is trained with several samples of those 12 notes played by some instrument (one note at a time), and a few samples of "silence".
The results are actually good. The network is able to detect those notes played by different instruments preety accurately, it's relatively amune to noise, and even doesn't loose it's sanety completely when being played a song.
The goal, however, is to be able to detect polyphonic sound. So that when two or more notes are played together, the two corresponding neurons will fire. The surprising thing is that the network actually already does that to some extent (being trained over monophonic samples only), however less consistently and less accurately than for monophonic notes. My question is how can I enhance it's ability to recognise polyphnic sound?
The problem is I don't truely understand why it actually works already. The different notes (or their DFTs) are basically different points in space for which the network is trained. So I see why it does recognise similiar sounds (nearby points), but not how it "concludes" the output for a combination of notes (which form a distant point from each of the training examples). The same way an AND network which is trained over (0,0) (0,1) (1,0) = (0), is not expected to "conclude" that (1,1) = (1).
The brute force aprroach to this is to train the network with as many polyphonic samples as possible. However, since the network seem to somehow vaguely grasp the idea from the monophonic samples, there's probably something more fundemential here.
Any pointers? (sorry for the length, btw :).
The reason it works already is probably quite simply that you didn't train it to pick one and only one output (at least I assume you didn't). In the simple case when the output is just a dot product of the input and the weights, the weights would become matched filters for the corresponding pitch. Since everything is linear, multiple outputs would simultaneously get activated if multiple matched filters simultaneously saw good matches (as is the case for polyphonic notes). Since your network probably includes nonlinearities, the picture is a bit more complex, but the idea is probably the same.
Regarding ways to improve it, training with polyphonic samples is certainly one possibility. Another possibility is to switch to a linear filter. The DFT of a polyphonic sound is basically the sum of DFTs of each individual sound. You want a linear combination of inputs to become a corresponding linear combination of outputs, so a linear filter is appropriate.
Incidentally, why do you use a neural network for this in the first place? It seems that just looking at the DFT and, say, taking the maximum frequency would give you better results more easily.
Anssi Klapuri is a well-respected audio researcher who has published a method to perform pitch detection upon polyphonic recordings using Neural Networks.
You might want to compare Klapuri's method to yours. It is fully described in his master's thesis, Signal Processing Methods for the Automatic Transcription of Music. You can find his many papers online, or buy his book which explains his algorithm and test results. His master's thesis is linked below.
https://www.cs.tut.fi/sgn/arg/klap/phd/klap_phd.pdf
Pitch Detection upon polyphonic recordings is a very difficult topic and contains many controversies -- be prepared to do a lot of reading. The link below contains another approach to pitch detection upon polyphonic recordings which I developed for a free app called PitchScope Player. My C++ source code is available on GitHub.com, and is referenced within the link below. A free executable version of PitchScope Player is also available on the web and runs on Windows.
Real time pitch detection
I experimented with evolving a CTRNN (Continuous Time Recurrent Neural Network) on detecting the difference between 2 sine waves. I had moderate success, but never had time to follow up with a bank of these neurons (ie in bands similar to the cochlear).
One possible approach would be to employ Genetic Programming (GP), to generate short snippets of code that detects the pitch. This way you would be able to generate a rule for how the pitch detection works, which would hopefully be human readable.

Resources