this question may come as being too broad, but I will try to make every sub-topic to be as specific as possible.
My setting:
Large binary input (2-4 KB per sample) (no images)
Large binary output of the same size
My target: Using Deep Learning to find a mapping function from my binary input to the binary output.
I have already generated a large training set (> 1'000'000 samples), and can easily generate more.
In my (admittedly limited) knowledge of Neural networks and deep learning, my plan was to build a network with 2000 or 4000 input nodes, the same number of output nodes and try different amounts of hidden layers.
Then train the network on my data set (waiting several weeks if necessary), and checking whether there is a correlation between in- and output.
Would it be better to input my binary data as single bits into the net, or as larger entities (like 16 bits at a time, etc)?
For bit-by-bit input:
I have tried "Neural Designer", but the software crashes when I try to load my data set (even on small ones with 6 rows), and I had to edit the project save files to set Input and Target properties. And then it crashes again.
I have tried OpenNN, but it tries to allocate a matrix of size (hidden_layers * input nodes) ^ 2, which, of course, fails (sorry, no 117GB of RAM available).
Is there a suitable open-source framework available for this kind of
binary mapping function regression? Do I have to implement my own?
Is Deep learning the right approach?
Has anyone experience with these kind of tasks?
Sadly, I could not find any papers on deep learning + binary mapping.
I will gladly add further information, if requested.
Thank you for providing guidance to a noob.
You have a dataset containing pairs of binary valued vectors, with a max length of 4,000 bits. You want to create a mapping function between the pairs. On the surface, that doesn't seem unreasonable - imagine a 64x64 image with binary pixels – this only contains 4,096 bits of data and is well within the reach of modern neural networks.
As your dealing with binary values, then a multi-layered Restricted Boltzmann Machine would seem like a good choice. How many layers you add to the network really depends on the level of abstraction in the data.
You don’t mention the source of the data, but I assume you expect there to be a decent correlation. Assuming the location of each bit is arbitrary and is independent of its near neighbours, I would rule out a convolutional neural network.
A good open source framework to experiment with is Torch - a scientific computing framework with wide support for machine learning algorithms. It has the added benefit of utilising your GPU to speed up processing thanks to its CUDA implementation. This would hopefully avoid you waiting several weeks for a result.
If you provide more background, then maybe we can home in on a solution…
Related
I have a problem that I don't have enough training data for my NN. It is trying to predict the result of a soccer game given the last games which I woulf say is a regression task.
The training data are results of soccer games of the last 15 seasons (which are about 4500 games). Getting to new data would be hard and would take a lot of time.
What should I do now?
Is it good to duplicate the data?
Should I input randomized data? (Maybe noise but I'm not quite sure what that is)
If there is no way of creating more data,
I should probably turn up the learning rate right? (I have it sitting at 0.01 and the momentum at 0.9)
I am using mini batches consisting of 32 training datas in training. Since I don't have a lot of training I don't have a lot of mini batches. Should I stop using them?
To start from the beginning: This is a very theoretical question and is not directly related to programming, which I recommend (in future) to post over at the Data Science Stackexchange.
To go into your problem: 4500 samples is not as bad as it sounds, depending on the exact task at hand. Are you trying to predict the match results (i.e. which team is the winner?), are you looking for more specific predictions (across a lot of different, specific teams)?
If you can make sure that you have a reasonable amount of data per class, one can work with a number of samples lower than what you have. Simply duplicating the data will not help you much, since you are very likely to just overfit on the samples you are seeing, without much of an improvement; Or rather, you will get the same results as training over a longer period (since essentially you see every sample twice per epoch, instead of one).
Again, what usually happens after long training periods is overfitting, so nothing gained here.
Your second suggestion is generally called data augmentation. Instead of simply copying samples, you alter them enough to make it look "different" to the network. But be careful! Data augmentation works well for some inputs, like images, since the change in input is significant enough to not represent the same sample, but still contains meaningful information about the class (a horizontally mirrored image of a cat still shows a "valid cat", unlike a vertically mirrored image, which is more unrealistic in the real world).
Essentially, it depends on your input features to determine where it makes sense to add noise. If you are only changing the results of the previous game, a minor change in input (adding/subtracting one goal at random) can significantly change the prediction you make.
If you slightly scramble ELO scores by a random number, on the other hand, the input value will not be too different, "but different enough" to use it as a novel example.
Turning up the learning rate is not a good idea, since you are essentially just letting the network converge more towards the specific samples. On the contrary, I would argue that the current learning rate is still too high, and you should certainly not increase it.
Regarding mini batches, I think I have referenced this a million times now, but always consider smaller minibatches. From a theoretical point of view, you are more likely to converge to a local minimum.
I'm working on pre-processing image compression session. I'm researching on image compression methods and read lot of articles about jpeg2000 image compression. But I can't find clear resource about choosing bitrate for different layer of color image and bitrate calculation methods in jpeg2000.
Please give me some clues with official references on that.
There is not a single correct answer. The number of layers and the bit rates associated with those layers should be set according to the needs of the users and systems which will consume the imagery.
The good news is that there is plenty of guidance! Here are two options.
Copy Kakadu
Take a look at this gist. It shows the input parameters for Kakadu's kdu_compress utility. For the -rate flag it states:
When two rates are specified, the number of layers must be 2 or more
and intervening layers will be assigned roughly logarithmically spaced
bit-rates. When only one rate is specified, an internal heuristic
determines a lower bound and logarithmically spaces the layer rates
over the range.
Kakadu is heavily used in industry and their J2K compression software is highly trusted. So if they software uses logarithmic spacing for their quality layers that might be a reasonable place to start.
Pick a profile in the BIIF Profile for JPEG 2000
On the other hand, you can take a look at the BIIF Profile for JPEG 2000 which provides several compression profiles for different situations. The profiles provides examples giving the number of layers and bit rates. That said, there is a general message across all the profiles such as:
D.4.7 (NPJE profile) of BIIF:
Some systems may change the exact bitrates and number of layers to
meet application requirements or quality requirements.
F.7 (TPJE profile) of BIIF:
Note that the actual target bit rates and numbers of Quality Layers
used for a specific sensor would need to be optimized to accommodate
any unique properties of that particular imagery collection system.
G.2.1.2 (LPJE profile) of BIIF:
Applications need a sufficient number of codestream layers for optimal
bandwidth and memory management across such a wide range of
resolutions. Layers provide an elegant means to control visual quality
and manage channel capacity for streaming compressed imagery over low
bandwidth links... LPJE does not require a specific layer structure
since the goal of this preferred encoding is to accommodate hardware
and software implementations.
Using Matlab, I am going to generate several data files and store them in H5 format as 20x1500xN, where N is an integer that can vary, but typically around 2300. Each file will have 4 different data sets with equal structure. Thus, I will quickly achieve a storage problem. My two questions:
Is there any reason not the split the 4 different data sets, and just save as 4x20x1500xNinstead? I would prefer having them split, since it is different signal modalities, but if there is any computational/compression advantage to not having them separated, I will join them.
Using Matlab's built-in compression, I set deflate=9 (and DataType=single). However, I have now realized that using deflate multiplies my computational time with 5. I realize this could have something to do with my ChunkSize, which I just put to 20x1500x5 - without any reasoning behind it. Is there a strategic way to optimize computational load w.r.t. deflation and compression time?
Thank you.
1- Splitting or merging? It won't make a difference in the compression procedure, since it is performed in blocks.
2- Your choice of chunkshape seems, indeed, bad. Chunksize determines the shape and size of each block that will be compressed independently. The bad is that each chunk is of 600 kB, that is much larger than the L2 cache, so your CPU is likely twiddling its fingers, waiting for data to come in. Depending on the nature of your data and the usage pattern you will use the most (read the whole array at once, random reads, sequential reads...) you may want to target the L1 or L2 sizes, or something in between. Here are some experiments done with a Python library that may serve you as a guide.
Once you have selected your chunksize (how many bytes will your compression blocks have), you have to choose a chunkshape. I'd recommend the shape that most closely fits your reading pattern, if you are doing partial reads, or filling in in a fastest-axis-first if you want to read the whole array at once. In your case, this will be something like 1x1500x10, I think (second axis being the fastest, last one the second fastest, and fist the slowest, change if I am mistaken).
Lastly, keep in mind that the details are quite dependant on the specific machine you run it: the CPU, the quality and load of the hard drive or SSD, speed of RAM... so the fine tuning will always require some experimentation.
Just starting to play around with Neural Networks for fun after playing with some basic linear regression. I am an English teacher so don't have a math background and trying to read a book on this stuff is way over my head. I thought this would be a better avenue to get some basic questions answered (even though I suspect there is no easy answer). Just looking for some general guidance put in layman's terms. I am using a trial version of an Excel Add-In called NEURO XL. I apologize if these questions are too "elementary."
My first project is related to predicting a student's Verbal score on the SAT based on a number of test scores, GPA, practice exam scores, etc. as well as some qualitative data (gender: M=1, F=0; took SAT prep class: Y=1, N=0; plays varsity sports: Y=1, N=0).
In total, I have 21 variables that I would like to feed into the network, with the output being the actual score (200-800).
I have 9000 records of data spanning many years/students. Here are my questions:
How many records of the 9000 should I use to train the network?
1a. Should I completely randomize the selection of this training data or be more involved and make sure I include a variety of output scores and a wide range of each of the input variables?
If I split the data into an even number, say 9x1000 (or however many) and created a network for each one, then tested the results of each of these 9 on the other 8 sets to see which had the lowest MSE across the samples, would this be a valid way to "choose" the best network if I wanted to predict the scores for my incoming students (not included in this data at all)?
Since the scores on the tests that I am using as inputs vary in scale (some are on 1-100, and others 1-20 for example), should I normalize all of the inputs to their respective z-scores? When is this recommended vs not recommended?
I am predicting the actual score, but in reality, I'm NOT that concerned about the exact score but more of a range. Would my network be more accurate if I grouped the output scores into buckets and then tried to predict this number instead of the actual score?
E.g.
750-800 = 10
700-740 = 9
etc.
Is there any benefit to doing this or should I just go ahead and try to predict the exact score?
What if ALL I cared about was whether or not the score was above or below 600. Would I then just make the output 0(below 600) or 1(above 600)?
5a. I read somewhere that it's not good to use 0 and 1, but instead 0.1 and 0.9 - why is that?
5b. What about -1(below 600), 0(exactly 600), 1(above 600), would this work?
5c. Would the network always output -1, 0, 1 - or would it output fractions that I would then have to roundup or rounddown to finalize the prediction?
Once I have found the "best" network from Question #3, would I then play around with the different parameters (number of epochs, number of neurons in hidden layer, momentum, learning rate, etc.) to optimize this further?
6a. What about the Activation Function? Will Log-sigmoid do the trick or should I try the other options my software has as well (threshold, hyperbolic tangent, zero-based log-sigmoid).
6b. What is the difference between log-sigmoid and zero-based log-sigmoid?
Thanks!
First a little bit of meta content about the question itself (and not about the answers to your questions).
I have to laugh a little that you say 'I apologize if these questions are too "elementary."' and then proceed to ask the single most thorough and well thought out question I've seen as someone's first post on SO.
I wouldn't be too worried that you'll have people looking down their noses at you for asking this stuff.
This is a pretty big question in terms of the depth and range of knowledge required, especially the statistical knowledge needed and familiarity with Neural Networks.
You may want to try breaking this up into several questions distributed across the different StackExchange sites.
Off the top of my head, some of it definitely belongs on the statistics StackExchange, Cross Validated: https://stats.stackexchange.com/
You might also want to try out https://datascience.stackexchange.com/ , a beta site specifically targeting machine learning and related areas.
That said, there is some of this that I think I can help to answer.
Anything I haven't answered is something I don't feel qualified to help you with.
Question 1
How many records of the 9000 should I use to train the network? 1a. Should I completely randomize the selection of this training data or be more involved and make sure I include a variety of output scores and a wide range of each of the input variables?
Randomizing the selection of training data is probably not a good idea.
Keep in mind that truly random data includes clusters.
A random selection of students could happen to consist solely of those who scored above a 30 on the ACT exams, which could potentially result in a bias in your result.
Likewise, if you only select students whose SAT scores were below 700, the classifier you build won't have any capacity to distinguish between a student expected to score 720 and a student expected to score 780 -- they'll look the same to the classifier because it was trained without the relevant information.
You want to ensure a representative sample of your different inputs and your different outputs.
Because you're dealing with input variables that may be correlated, you shouldn't try to do anything too complex in selecting this data, or you could mistakenly introduce another bias in your inputs.
Namely, you don't want to select a training data set that consists largely of outliers.
I would recommend trying to ensure that your inputs cover all possible values for all of the variables you are observing, and all possible results for the output (the SAT scores), without constraining how these requirements are satisfied.
I'm sure there are algorithms out there designed to do exactly this, but I don't know them myself -- possibly a good question in and of itself for Cross Validated.
Question 3
Since the scores on the tests that I am using as inputs vary in scale (some are on 1-100, and others 1-20 for example), should I normalize all of the inputs to their respective z-scores? When is this recommended vs not recommended?
My understanding is that this is not recommended as the input to a Nerual Network, but I may be wrong.
The convergence of the network should handle this for you.
Every node in the network will assign a weight to its inputs, multiply them by their weights, and sum those products as a core part of its computation.
That means that every node in the network is searching for some coefficients for each of their inputs.
To do this, all inputs will be converted to numeric values -- so conditions like gender will be translated into "0=MALE,1=FEMALE" or something similar.
For example, a node's metric might look like this at a given point in time:
2*ACT_SCORE + 0*GENDER + (-5)*VARISTY_SPORTS ...
The coefficients for each values are exactly what the network is searching for as it converges.
If you change the scale of a value, like ACT_SCORE, you just change the scale of the coefficient that will be found by the reciporical of that scaling factor.
The result should still be the same.
There are other concerns in terms of accuracy (computers have limited capacity to represent small fractions) and speed that may enter this, but not being familiar with NEURO XL, I can't say whether or not they apply for this technology.
Question 4
I am predicting the actual score, but in reality, I'm NOT that concerned about the exact score but more of a range. Would my network be more accurate if I grouped the output scores into buckets and then tried to predict this number instead of the actual score?
This will reduce accuracy, although you should converge to a solution much faster with fewer possible outputs (scores).
Neural Networks actually describe very high-dimensional functions in their input variables.
If you reduce the granularity of that function's output space, you essentially state that you don't care about local minima and maxima in that function, especially around the borders between your output scores.
As a result, you are sacrificing information that may be an essential component of the "true" function that you are searching for.
I hope this has been helpful, but you really should break this question down into its many components and ask them separately on different sites -- potentially some of them do belong here on StackOverflow as well.
I saw different articles speaking about OCR form recognition (data extraction) and they said that they used Neural Network in order to do form recognition, so what's the relation between Artificial Neural network (ANN) and form recognition? If I want to extract fields from a BusinessCard, is it required to use ANN or is it optional? In other words when do I need to use ANN and when I don't?
It's a little different. ANN is just an "expert" in all OCR. But OCR engines contain many experts. When you study ANN you will build a simple OCR engine using just ANN but this does not compare to modern engines that use this in conjunction with tri-grams, morphology, data types ( very important for BCR and Forms ), dictionaries, connected components algorithm, etc. So look at it as just one of the tools in the bag of tricks to extract quality results. A good engine will incorporate ANN and all the others. In BCR there are additional considerations and it should be very heavy on connected components, dictionaries first, then use ANN and pattern matching for the actually recognition.
ANN is one way to perform OCR. There are others. Hence if you want to extract fields from a BusinessCard using ANN is only optional.
Good question. I recently spent some time playing with OCRopus, a Google project that does OCR - you can get it for free and play with it yourself. I'm pretty sure that it has an ANN as one of the modules behind it. However, the whole process of Optical Character Recognition can have many steps (lots of different little modules that each do something and pass the results to the next module).
So, here are some of the things I remember as being done by modules in that project:
There was a module that turned the image into black and white - this makes it easier for later modules to deal with.
Getting rid of speckles / spackles.
Straightening out the lines of text.
Breaking lines of text into individual words (it's been a few weeks, not sure about this one)
Basically, you can do the above using little bits of code that don't involve a neural net. So it's simpler doing it with these little bits of code.
The neural net I think is used just to recognize the individual characters - which character of a group of possible characters is it.
There's a training command in the OCRopus that I had running for over a week on end, and it kept sending line samples to the map, slowly changing the map as it went. I think it was training the ANN part.