Databases
StackOverflow2013
Postsdbo
PO
 

Note that there are some explanatory texts on larger screens.

plurals
  1. PO
    primarykey
    data
    text
    <p>You didn't say whether you can use an existing framework or need to implement the solution from scratch, but either way Python is excellent language for coding neural networks.</p> <p>If you can use a framework, check out Theano, which is written in Python and is the most complete neural network framework available in any language:</p> <p><a href="http://www.deeplearning.net/software/theano/" rel="nofollow">http://www.deeplearning.net/software/theano/</a></p> <p>If you need to write your implementation from scratch, look at the book 'Machine Learning, An Algorithmic Perspective' by Stephen Marsland. It contains example Python code for implementing a basic multilayered neural network.</p> <p>As for how to proceed, you'll want to convert your images into 1-D input vectors. Don't worry about losing the 2-D information, the network will learn 'receptive fields' on its own that extract 2-D features. Normalize the pixel intensities to a -1 to 1 range (or better yet, 0 mean with a standard deviation of 1). If the images are already centered and normalized to roughly the same size than a simple feed-forward network should be sufficient. If the cars vary wildly in angle or distance from the camera, you may need to use a convolutional neural network, but that's much more complex to implement (there are examples in the Theano documentation). For a basic feed-forward network try using two hidden layers and anywhere from 0.5 to 1.5 x the number of pixels in each layer. </p> <p>Break your dataset into separate training, validation, and testing sets (perhaps with a 0.6, 0.2, 0.2 ratio respectively) and make sure each image only appears in one set. Train ONLY on the training set, and don't use any regularization until you're getting close to 100% of the training instances correct. You can use the validation set to monitor progress on instances that you're not training on. Performance should be worse on the validation set than the training set. Stop training when the performance on the validation set stops improving. Once you've accomplished this you can try different regularization constants and choose the one that results in the best validation set performance. The test set will tell you how well your final result is performing (but don't change anything based on test set results, or you risk overfitting to that too!). </p> <p>If your car images are very complex and varied and you cannot get a basic feed-forward net to perform well, you might consider using 'deep learning'. That is, add more layers and pre-train them using unsupervised training. There's a detailed tutorial on how to do this here (though all the code examples are in MatLab/Octave):</p> <p><a href="http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial" rel="nofollow">http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial</a></p> <p>Again, that adds a lot of complexity. Try it with a basic feed-forward NN first.</p>
    singulars
    1. This table or related slice is empty.
    1. POvehicle type identification with neural network
      singulars
      1. PTQuestion
    1. PTAnswer
    1. This table or related slice is empty.
    1. USJMB
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. POvehicle type identification with neural network
      singulars
      1. PTQuestion
    1. This table or related slice is empty.
    1. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTUpMod
    2. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTUpMod
    3. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTAcceptedByOriginator
    1. COActually it is not necessary to implement my own neural network but I would prefer to do it myself as I will learn a lot..
      singulars
      1. PO
      1. USadil
    2. COIs regularization==biasing here?
      singulars
      1. PO
      1. USadil
    3. CONo, regularization is an extra term in the error function that gives a weight penalty to prevent large weights. This is one of several ways to prevent overfitting. However, you can ignore regularization to start. Until you get a network that can learn the training data you don't need worry about overfitting.
      singulars
      1. PO
      1. USJMB
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload