40m QIL Cryo_Lab CTN SUS_Lab TCS_Lab OMC_Lab CRIME_Lab FEA ENG_Labs OptContFac Mariner WBEEShop
  40m Log  Not logged in ELOG logo
Message ID: 13937     Entry time: Sun Jun 10 15:04:33 2018
Author: pooja 
Type: Update 
Category: Cameras 
Subject: Developing neural network 

Aim: To develop a neural network in order to correlate the intensity fluctuations in the scattered light to the angular motion of the test mass. A block diagram of the technique employed is given in Attachment 1.

I have used Keras to implement supervised learning using neural network (NN). Initially I had developed a python code that converts a video (59 sec) of scattered light, after an excitation (sine wave of frequency 0.2 Hz) is applied to ETMX pitch, to image frames (of size 480*720)  and stores the 2D pixel values of 1791 images frames captured into an hdf5 file. This array of shape (1791,36500) is given as an input to the neural network. I have tried to implement regular NN only, not convolution or recurrent NN. I have used sequential model in Keras to do this. I have tried with various number of dense layers and varied the number of nodes in each layer. I got test accuracy of approximately 7% using the following network. There are two dense layers, first one with 750 nodes with a dropout of 0.1 ( 10% of the nodes not used) and second one with 500 nodes. To add nonlinearity to the network, both the layers are given an activation function of tanh. The output layer has 1 node and expects an output of shape (1791,1). This model has been compiled with a loss function of categorical crossentropy, optimizer = RMSprop. We have used these since they have been mostly used in the image analysis examples. Then the model is trained against the dataset of mirror motion. This has been obtained by sampling the cosine wave fit to the mirror motion so that the shapes of the input and output of NN are consistent. I have used a batch size ( number of samples per gradient update) = 32 and epochs (number of times entire dataset passes through NN) = 20. However, using this we got an accuracy of only 7.6%. 

I think that the above technique gives overfitting since dense layers use all the nodes during training apart from giving a dropout. Also, the beam spot moves in the video. So it may be necessary to use convolution NN to extract the information.

The video file can be accesses from this link https://drive.google.com/file/d/1VbXcPTfC9GH2ttZNWM7Lg0RqD7qiCZuA/view.

Gabriele told us that he had used the beam spot motion to train the neural network. Also he informed that GPUs are necessary for this. So we have to figure out a better way to train the network.  


gautam noon 11Jun: This link explains why the straight-up fully connected NN architecture is ill-suited for the kind of application we have in mind. Discussing with Gabriele, he informed us that training on a GPU machine with 1000 images took a few hours. I'm not sure what the CPU/GPU scaling is for this application, but given that he trained for 10000 epochs, and we see that training for 20 epochs on Optimus already takes ~30minutes, seems like a futile exercise to keep trying on CPU machines.

Attachment 1: nn_block_diag_2.pdf  31 kB  Uploaded Sun Jun 10 16:45:41 2018  | Hide | Hide all
nn_block_diag_2.pdf
ELOG V3.1.3-