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 9 months ago.
Improve this question
The TensorFlow home page describes its purpose as 'a software library for numerical computation'. Looking through the sample problems it looks like a problem is always formulated as follows:
Input
Model parameters
Desired output
Given some training data for 1) and 3), 2) can be computed.
I can see how this can be used to create bots, self-driving cars, image classifiers etc.
Given the broad definition of 'numerical computation', am I missing a class of other problems this can be used for? Can this be used for, say, more classical numerical computations such as the airflow around an aircraft or deformation of a structure under stress? Do you have any examples of how these classical problems would have to be formulated to fit the form above?
A nice discussion on what artificial neural networks could do, the fact that our brain is a neural network might imply that eventually an artificial neural network will be able to to the same tasks.
Some more examples of artificial neural networks used today: music creation, image based location, page rank, google voice, stock trade predictions, nasa star classifiaction, traffic management
Some fields i know of but do not have a good reference for:
optical quantum mechanics test set-up generator
medical diagnosis, reference only about safety
The Sharp LogiCook microwave oven, wiki, nasa mention
I think there are many millions of "problems" that can be solved with an ANN, deciding on the data representation (input,output) will be a challenge for some of these. some useful and useless examples i have been thinking about:
home thermostat that learns your wishes with certain weather types.
bakery production prediction
recognize go-stones on a board and map their locations
personal activity guesser and turn on appropriate device.
recognize person based on mouse movement
Given the right data and network these examples will work.
Dad has a pc controlling the heating system back home, i trained a network based on his 10years of heating data (outside temp, inside temp, humidity etc.) unfortunately i am not allowed to hook it up.
My aunt and uncle have a bakery, based on 6years of sales data i trained a network predicting how many breads and buns they should make. It showed me how important the correct inputs are. first i used the day of the year but when i switched to day of the week i saw a 15% increase in accuracy.
Currently i am working on a network that will detect a go board in a given image and map all 361 locations telling me if there is a black, white or no stone present.
Two examples that showed me how much information can be stored in a single neuron and of different ways to represent data:
Image example, neuron example (unfortunately you have to train both examples yourself so give them a little time.)
On to your example airflow around an aircraft.
I know none to nothing about airflow calculations and my try would be a really huge 3D input layer where you can "draw" an airplane and the direction and speed of the airflow.
It might work but it will require a tremendous amount of computation power, somebody knowing more about this specific topic probably knows a more abstract way of representing the data resulting in a more manageable network.
This nasa paper talks about a neural network for calculating airflow around a wing. Unfortunately i do not understand what kind of input they use, maybe it is more clear to you.
Related
I'm looking into designing a software platform that will aid linguists and anthropologists in their study of previously unstudied languages. Statistics show that around 1,000 languages exist that have never been studied by a person outside of their respective speaker groups.
My goal is to utilize TensorFlow to make a platform that will allow linguists to study and document these languages more efficiently, and to help them create written systems for the ones that don't have a written system already. One of their current methods of accomplishing such a task is three-fold: 1) Record a native speaker conversing in the language, 2) Listening to that recording and trying to transcribe it into the IPA, 3) From the phonetics, analyzing the phonemics and phonotactics of the language to eventually create a written system for the speaker.
My proposed platform would cut that research time down from a minimum of a year to a maximum of six months. Before I start, I have some questions...
What would be required to train TensorFlow to transcribe live audio into the IPA? Has this already been done? and if so, how would I utilize a previous solution for this project? Is a project like this even possible with TensorFlow? if not, what would you recommend using instead?
My apologies for the magnitude of this question. I don't have much experience in the realm of machine learning, as I am just beginning the research process for this project. Any help is appreciated!
I guess I will take a first shot at answering this. Since the question is pretty general, my answer will have to be pretty general as well.
What would be required. At the very least you would have to have a large dataset of pre-transcribed data. Ideally a large amount of spoken language audio mapped to characters in the phonetic alphabet, so the system could learn the sound of individual characters rather than whole transcribed words. If such a dataset doesn't exist, a less granular dataset could be used, mapping single words to their transcriptions. Then you would need a model, that is the actual neural network architecture implemented in code. And lastly you would need some computing resources. This is not something you can train casually, you would either have to buy some time in a cloud based machine learning framework (like Google Cloud ML) or build a fairly expensive machine to train at home.
Has this been done? I don't know. I don't think so. There have been published papers reporting various degrees of success at training systems to transcribe speech. Here is one, for example, http://deeplearning.stanford.edu/lexfree/lexfree.pdf It seems that since the alphabet you want to transcribe to is specifically designed to capture the way words sound rather than just write down the words you might have more success at training such a model.
Is it possible with TensorFlow. Yes, most likely. TensorFlow is well suited for implementing most modern deep learning architectures. Unless you end up designing some really weird and very original model for this purpose, TensorFlow should work just fine.
Edit: after some thought in part 1, you would have to use a dataset mapping spoken words to their transcriptions, since I expect that the same sound pronounced separately would be different from when the same sound is used in a word.
This has actually been done, albeit in PyTorch, by a group at CMU: https://github.com/xinjli/allosaurus
I'm participating in small data analysis competition in our school.
We use Fitbit wearable devices, which is loaned to each participants by host of contest.
For 2 months during the contest, they walk and sleep with this small device 24/7,
allow it to gather data about participant's walk count with heart rate(bpm), etc.
and we need to solve some problems based on these participants' data
like, example,
show the relations between rainy days and participants' working out rate using the chart,
i think purpose of problem is,
because of rain, lot of participants are expected to be at home.
can you show some cause and effect numerically?
i'm now studying python library numpy, pandas with ipython notebook.
but still i have no idea about solving these problems..
could you recommend some projects or sites use for references? i really eager to win this competition.:(
and lastly, sorry for my poor English.
Thank you.
that's a fun project. I'm working on something kind of similar.
Here's what you need to do:
Learn the fitbit API and stream the data from the fitbit accelerometer and gyroscope. If you can combine this with heart rate data, great. The more types of data you have, the more effective your algorithm will be. You can store this data in a simple csv file (streaming the accel/gyro data at 50Hz is recommended). Or setup a web server and store it in a database for easy access
Learn how to use pandas and scikit learn
[optional but recommended]: Learn matplotlib so you can graph you data and get a feel for how it looks
Load the data into pandas and create features on the data - notably using 1-2 second sliding window analysis with 50% overlap. Good features include (for all three Accel X, Y, Z): max, min, standard deviation, root mean square, root sum square and tilt. Polynomials will help.
Since this is a supervised classification problem, you will need to create some labelled data - so do this manually (state 1 = rainy day, state 2 = non-rainy day) and then train a classification algorithm. I would recommend a random forest
Test using unlabeled data - don't forget to use cross validation
Voila, you now have a highly accurate model and will win the competition. Plus you've learned about a bunch of really cool Python and machine learning stuff.
For more tutorials on how all this stuff works, I'd highly recommend the Kaggle tutorial projects
BONUS: If you want to take it to a new level, you can start adding smoothers on top of your classifier, for example by using a Hidden Markov Model as explained in this talk
BONUS 2: Go get a PhD in Human Activity Recognition.
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 8 years ago.
Improve this question
We are students trying to handling data size of about 140 million records and trying to run few machine learning algorithms. we are newbie to the entire cloud solutions and mahout implementations.Currently we have set them up in postgresql database but the current implementation doesn't scale up and read/write operations seems to be extremely slow after numerous performance tuning.Hence we are planning to go for cloud based services.
We have explored a few possible alternatives.
Amazon cloud based services( Mahout implementation)
Picloud with scikits learn (we were planning to use HDF5 format with NumPy)
Please recommend any other alternatives if any.
Here are the following questions
Which would yield us better results(turn around time) and would be cost effective? Please do mention us any other alternatives present.
In case if we set up amazon services how should we have the data format? If we use dynamodb will the cost shoot up?
Thanks
It depends on the nature of the machine learning problem you want to solve. I would recommend you to first subsample your dataset to something that fits in memory (e.g. 100k samples with a few hundred non-zero features per samples assuming a sparse representation).
Then try a couple of machine learning algorithms that scale to large number of samples in scikit-learn:
SGDClassifier or MultinomialNB if you want to do supervised classification (if you have categorical labels to predict in your dataset)
SGDRegressor if you want to do supervised regression (if you have continuous target variable to predict)
MiniBatchKMeans clustering to do unsupervised clustering (but then there is no objective way to quantify the quality of the resulting clusters by default).
...
Perform grid search to find the optimal values of the hyperparameters of the model (e.g. the regularizer alpha and the number of passes n_iter for SGDClassifier) and evaluate the performance using cross-validation.
Once done, retry with 2x larger dataset (still fitting in memory) and see if it improves you predictive accuracy significantly. If it's not the case then don't waste your time trying to parallelize this on a cluster to run that on the full dataset as it won't yield any better results.
If it does what you could do, is shard the data into pieces, then slices of data on each nodes, learn of SGDClassifier or SGDRegressor model on each node independently with picloud and collect back the weights (coef_ and intercept_) and then compute the average weights to build the final linear model and evaluate it on some held out slice of your dataset.
To learn more about the error analysis. Have look at how to plot learning curves:
http://digitheadslabnotebook.blogspot.fr/2011/12/practical-advice-for-applying-machine.html
https://gist.github.com/1540431
http://jakevdp.github.com/tutorial/astronomy/practical.html#bias-variance-over-fitting-and-under-fitting
PiCloud is built on top of AWS, so either way you're going to be using Amazon at the end of the day. The question is how much infrastructure you'll have to write yourself to get everything wired together. PiCloud gives some free usage to put it through the paces so you might give it shot initially. I haven't used it myself but clearly they're trying to provide ease of deployment for machine-learning type applications.
It seems like this is trying for results, not to be a cloud project, so I would either look into using one of Amazon's other services besides straight EC2 or otherwise some other software like PiCloud or Heroku or other service that can take care of the bootstrapping.
AWS has a program in place for supporting educational users, so you might want to do some research into that program.
You should take a look at numba if you are looking for some Numpy speed ups:
https://github.com/numba/numba
Doesn't solve your cloud scaling issue, but may reduce time to compute.
I just made a comparison between PiCloud & Amazon EC2 > might be helpful.
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'm looking for a way to determine whether a picture is explicit (is Safe For Work ) or not.
I am currently looking for an API that is capable of doing it, but so far I didn't have any success.
One of the ideas I had was to use the google search API and provide a URL to a picture, and looking whether or not it is in the results when safeSearch is enabled, but it will fail on a picture that was added before the crawler got to it.
Alternatively, I'm looking for pointers regarding what to look for in an image to determine how SFW it is. Any suggestions regarding shapes, colors or patterns?
As promised, a SFW paper from Google researchers and a patent for your study procured from this blog entry.
One of my colleagues led the development of the porn classification technology at one of the largest web companies. I will share what he told me about the development of the filter.
The definition of what is explicit varying greatly among jurisdictions so what is considered explicit in the US might not be in other parts of the world and vice-versa. So models need to take into account the users origin.
A purely imaged based approach is almost impossible to use effectively at web scale. The feature space is very complex in terms of how humans judge what is explicit and what is not and developing appropriate feature extraction technology for images proved to be exceedingly difficult.
Some of the most predictive features are the text on pages that link to the images. These are among the easiest features to develop also.
Building labeled training sets is very difficult since classifying porn and other explicit content for 8 hours a day tends to take a toll on the labelers. Because of this the turn over is fairly high with almost no one lasting a year.
Getting a high accuracy from the classifiers is still very, very difficult. They worked on it with several PhD's and a very experienced team and still did not achieve the accuracy that you are probably looking for.
If you have a more constrained problem space you can probably achieve a higher accuracy. If you are using image features only the algorithm or model will probably not generalize well and will have a high false positive rate. Best of luck.
See papers:
Detection of Pornographic Digital Images
Jorge A. Marcial-Basilio, Gualberto Aguilar-Torres, Gabriel Sánchez-Pérez, L. Karina Toscano-
Medina, and Héctor M. Pérez-Meana
Pornography Detection Using Support Vector Machine
Yu-Chun Lin (林語君) Hung-Wei Tseng (曾宏偉) Chiou-Shann Fuh
Image-Based Pornography Detection
Rigan Ap-apid
De La Salle University, Manila, Philippines
You can also take some hints from existing implementations e.g.:
"The Porn Detection Stick uses advanced image analyzing algorithms that categorize images as potentially harmful by identifying facial features, flesh tone colors, image back grounds, body part shapes, and more."
As it currently stands, this question is not a good fit for our Q&A format. We expect answers to be supported by facts, references, or expertise, but this question will likely solicit debate, arguments, polling, or extended discussion. If you feel that this question can be improved and possibly reopened, visit the help center for guidance.
Closed 9 years ago.
I'm looking for ideas for a Neural Networks project that I could complete in about a month or so. I'm doing it for the National Science Fair, so I need something that has some curb appeal as well since it's being judged.
It doesn't necessarily have to be completely new and unique, I'm just looking for ideas, but it should be complex enough that it would impress someone who knows about the field. My first idea was to implement a spam filter of sorts, but I recently found out that NN's aren't a very good way to do it. I've already got a basic NN simulator with Genetic Algorithms, and I'm also adding the the generic back-propagation algorithms as well.
Any ideas?
Look into Numenta's Hierarchical Temporal Memory (HTM) concept. This may be slightly off topic if the expectation is of "traditional" Neural Nets, but it is also an extremely promising avenue for Artificial Intelligence.
Although Numenta introduced HTM and its associated software platform, NuPIC, almost five years ago, the first commercial product based upon this technology was released (in beta) a few weeks ago by Vitamin D. It is called Vitamin D Video and essentially turns any webcam or IP camera into a sophisticated video monitoring system, recognizing classes of items (say persons vs. cats or other animals) in the video feed.
With the proper setup, this type of application could make for an interesting display at the Science Fair, one with much "curb appeal".
To wet your appetite or even get your feet wet with HTM technology you can download NuPIC and check its various sample applications. Chances are that you may find something that meets typical criteria of both geekness and coolness for science fairs.
Generally, HTMs aim at solving problems which are simple for humans but difficult for computers; such a statement is somewhat of a generic/applicable to Neural Nets, but HTMs take this to the "next level".
Although written in C (I think) NuPIC is typically interfaced in Python, which makes it a convenient test bed for simple yet sophisticated proofs of concept applications.
You could always try to play around with a neural network and stock courses, if I had a month of spare time for a neural network implementation, thats what I would play with.
A friend of mine in college wrote a NN to play go on a 9x9 board.
I don't think it ever got very good, but I think it would be fun to try.
Look on how a bidirectional associative memory compare with other classical edit distance algorithms (Levenshtein, Damerau-Levenshtein etc) for typo correction. Also consider the articles on hebbian unlearning while training your NN - it seems that the confabulation phenomena is avoided.
I've done some works on top of NN, mainly an XML based language (Neural XML). See details here
http://amazedsaint.blogspot.com/search/label/Neural%20Network
Also, one interesting .NET Neural network project is Aforge.net - Check out that as well..
You can implement the game Cellz or create a controller for it. It was first created by Simon M Lucas. It's a nice and interesting game, and i'm sure that everyone will love it. I used it also for a school project and it turned out very ok.
You can find in that page some links to other interesting games.
How about applying it to predicting exchange rate (USD - EUR for example for sub minute trading) should be fun to show net gain of money over 1 month.
I doubt this will work for trades longer than a minute... without a lot of extra work.
I like using committee machines so why not apply it to Face-Detection in images / movies or voice print authentication.
Finally you could get it to play pleasing music and use a crowd sourcing fitness function whereby people vote for the best "musicians"