-2

I have a dataset of the order of MxN. I want to perform a binary classifcation on this dataset using neural networks. I was looking into Recurrent Neural Networks. Although, LSTM's can be used for AutoEncoders, I am not sure if they can be used for classification (I am trying to do a binary classification). I am very new to neural networks and deep learning models and i am not really sure if there is a way of achieving binary classification with neural networks. I tried Bernouli RBM on my dataset. I am not sure how to use this model to perform classification. I also found out Pipeline(). Again, I am not sure how to achieve my goal.

Any help would be greatly appreciated.

prabhu
  • 369
  • 1
  • 4
  • 17

1 Answers1

0

Ok, something doesn't stack up. If you have unlabelled data and you want to classify it you must take a look at K-Means (http://scikit-learn.org/stable/modules/clustering.html#k-means).

Regarding LSTMs classification: You run your input through the RNN layers and take the last output and feed it into some Conv / Fully-connected layers to take care of classification as you know it.

Mihail Burduja
  • 3,196
  • 2
  • 22
  • 28
  • So, the dataset looks like this. It is Mx3xN matrix. where M is each subject and 3xN is the data collected for each of the subjects. Therefore I have M(subjects)x 3xN. Sorry, I had not described my dataset properly. My aim is to do like this: For each subject, I will divide the data into time slices (say, 10) I will use 8 time slices for training and the remaining 2 for prediction. The target i expect is a binary number indicating if the data contained in the time slices matches with any of the M subjects(if it matches with subject 1, or subject 2, ..., subject M). – prabhu Apr 05 '17 at 19:21
  • A simpler way to do this would be to formulate this task as traditional classification with 2^M classes. – txizzle Apr 05 '17 at 21:29