I am currently working on a poker AI and I am stuck on this question: What is the best way to encode poker cards for my AI? I am using deep reinforcement learning techniques and I just don't know how to anwser my question.
The card information is stored as a string. For example: "3H" would be "three of hearts". I thought about ranking the cards and then attaching values to them such that a high-rated card like AH ("Ace of hearts") would get a high number like 52 or something like that. The problem with this approach is that it doesn't take the suits into acccount.
I have seen some methods where they just assign a number to each and every card such that at the end there are 52 numbers from 0-51 (https://www.codewars.com/kata/52ebe4608567ade7d700044a/javascript). The problem I see with that is that my neural net wouldn't or at least have difficulties getting the connection between similar cards like Aces ('cause as in the link above one Ace is labeled with a 0 the other one with 13 etc.).
Can someone please help me with this question such that the encodings take care of the: suits, values, ranks, etc and my NN would be able to get the connections between similar cards.
Thanks in andvance
Related
I'm trying to create a calculator(real calculator), from scratch, with only simple parts (relay, diode, etc.). But I got to a chronic problem, how the hell do I convert binary numbers, ex:00101110 to decimal? so that I can make my display show 46 for example. Making the display translate a 0000...1001 (0...9) is easy, but what about after that? when a number comes with two or more decimal places (ex:10000000 =128). I know it can be tricky to explain, so is there somewhere I can find the answer, maybe a schematic?
This isn't a programming language, it's literally a relay computer (remember the old IBM, Harvard Mark I?). I just want to make a relay calculator that does binary calculations (the calculation part is theoretically finished. For now only sum.)
What I can't do is make the result in binary become something that can be shown on a 7segment display.
An easy example is: "0000 0111" this I can make the display show the number 7, because it has only one decimal place. Now with "0011 0100" the situation changes, the number would be 52, simply making the "52" appear on a display is not a challenge, the problem here is: how does a processor translate binary numbers from 0000 to infinity, in a way that can you put it on a display?
I don't necessarily need a definitive answer, whatever, even if a website, a book, a light at the end of the tunnel.
I want to predict the occurrences of the word "repeat" in a speech as well as the word's approximate duration. For this task, I'm planning to build a Deep Learning model. I've around 50 positive as well as 50 negative utterances (I couldn't collect more).
Initially I've searched for any pretrained models for keyword spotting, but I couldn't get a good one.
Then I tried Speech Recognition models (Deep Speech), but it couldn't predict the exact repeat words as my data follows Indian accent. Also, I've thought that going for ASR models for this task would be a over-killing one.
Now, I've split the entire audio into chunk of 1 secs with 50% overlapping and tried a binary audio classification in each chunk that is whether the chunk has the word "repeat" or not. For building the classification model, I calculated the MFCC features and build a sequence model on the top of it. Nothing seems to work for me.
If anyone already worked with this kind of task, please provide me with a correct method/resources to build a DL model for this task. Thanks in advance!
I need to convert a decimal number to a base between 2 and 9 using Little Man Computer. How do I proceed?
I believe successive divisions are the best method. In my opinion, I must write a code which divides two numbers, then save the integer ratio for the next division, as well as all of the remainders in an array of indefinite size, but I've been struggling with the division code for hours now. I tried searching for a code which divides two numbers, but all the ones I tried have mistakes/don't work. I'm stuck at the easiest part of the problem, I can't imagine how I'm ever going to be able to write a self-modifying code which manages an array of ever-increasing line positions and backtracks through it at the end to extract all the remainders. I'm at a loss here, any help would be appreciated.
I'm trying to develop a model to recognize new gestures with the Myo Armband. (It's an armband that possesses 8 electrical sensors and can recognize 5 hand gestures). I'd like to record the sensors' raw data for a new gesture and feed it to a model so it can recognize it.
I'm new to machine/deep learning and I'm using CNTK. I'm wondering what would be the best way to do it.
I'm struggling to understand how to create the trainer. The input data looks like something like that I'm thinking about using 20 sets of these 8 values (they're between -127 and 127). So one label is the output of 20 sets of values.
I don't really know how to do that, I've seen tutorials where images are linked with their label but it's not the same idea. And even after the training is done, how can I avoid the model to recognize this one gesture whatever I do since it's the only one it's been trained for.
An easy way to get you started would be to create 161 columns (8 columns for each of the 20 time steps + the designated label). You would rearrange the columns like
emg1_t01, emg2_t01, emg3_t01, ..., emg8_t20, gesture_id
This will give you the right 2D format to use different algorithms in sklearn as well as a feed forward neural network in CNTK. You would use the first 160 columns to predict the 161th one.
Once you have that working you can model your data to better represent the natural time series order it contains. You would move away from a 2D shape and instead create a 3D array to represent your data.
The first axis shows the number of samples
The second axis shows the number of time steps (20)
The thirst axis shows the number of sensors (8)
With this shape you're all set to use a 1D convolutional model (CNN) in CNTK that traverses the time axis to learn local patterns from one step to the next.
You might also want to look into RNNs which are often used to work with time series data. However, RNNs are sometimes hard to train and a recent paper suggests that CNNs should be the natural starting point to work with sequence data.
I have this idea to use CNN to learn a Belote Bidder.
We have 32 cards from which the bidder guy has only 5. I put them in an "image" 4x8, arr[r][s] = 1 if he has the card from suit s and rank r, and 0 if he doesnt.
Only 5 ones in the image.
Then I simulate N times the possible bids with Monte Carlo algorithm and make a vector with the probabilities for each bid. They sum to 1.
After this I try to learn the CNN but no matter what I do, it doesnt learn well and it doesnt generalize. Maybe the input data is not useful for CNN, perhaps I need to use something else, but the most important thing is - I need it to generalize well, because the computation of the output is very expensive, and I want to do it only once, save the CNN and then use it.