22253

How to normalize coordinates inputs for neural networks

Question:

I am doing project regrading signature recognition using Neural Networks.So in there I did all feature extraction activities.In result of feature extraction,there are some features which are as set of coordinates(x and y).So I know before put those as neural network input it should be normalize.So I don't know the exact way to normalize coordinates before it give as NN input.Is there are any method to approach that problem? Thank you.

Answer1:

Serialize 'em!

<br />

<h3>Given that your cluster algorithm returns data in this manner (or something similar)</h3> # output from |output coordinates # cluster algorithm | [_ X X _ _] (0,0) (0,1) (0,2) (0,3) (0,4) [_ X _ X _] (1,0) (1,1) (1,2) (1,3) (1,4) [_ X X _ _] (2,0) (2,1) (2,2) (2,3) (2,4) [_ X _ _ _] (3,0) (3,1) (3,2) (3,3) (3,4) [_ X _ _ _] (4,0) (4,1) (4,2) (4,3) (4,4)

<br />

<h3>Then we serialize it (that is: just concatinate the lines)</h3> # output from cluster algorithm, serialized: [_ X X _ _ _ X _ X _ _ X X _ _ _ X _ _ _ _ X _ _ _ ] # the corresponding coordinates for instructional purposes: [(0,0) (0,1) (0,2) (0,3) (0,4) (1,0) (1,1) (1,2) (1,3) (1,4) (2,0) (2,1) (2,2) (2,3) (2,4) (3,0) (3,1) (3,2) (3,3) (3,4) (4,0) (4,1) (4,2) (4,3) (4,4)]

<br /> And feed this into your network!

<hr /><h3>When it comes to normalization</h3>

Your clustering algorithm should "cluster your input images enough", so that the number of inputs is acceptable.

Recommend

  • Dealing with textual data for classification
  • Tensorflow: Trainable Variable Masking
  • Avoiding vanishing gradient in deep neural networks
  • Multi-Classification NN with Keras error
  • How to use previous output and hidden states from LSTM for the attention mechanism?
  • Hand written character recognition using neural network
  • Algorithm that Generates Unique Serial Number for Each English Word
  • Prime numbers using Sieve of Atkin with BigInteger
  • Extracting data from a string where the data structure is embedded in the string itself
  • d3.js - Tree Layout - How can I flip it?
  • Storing command output lines into array based on new line character
  • How to normalize a database schema
  • LibGdx GLES2.0 cube texel stretching
  • Android application not restoring state when installed from .apk, works fine from eclipse
  • How to load Q library with Require.js?
  • Receive list of elements in their visual order
  • Python cosine function precision [duplicate]
  • HttpClient: disabling chunked encoding
  • Private IP address in reserved subnet range
  • Trying to get the char code of ENTER key
  • gspread or such: help me get cell coordinates (not value)
  • Create DicomImage from scratch using Dcmtk
  • How to do unit test for HttpContext.Current.Server.MapPath
  • Java: can you cast Class into a specific interface?
  • Java Scanner input dilemma. Automatically inputs without allowing user to type
  • AES padding and writing the ciphertext to a disk file
  • Updating server-side rendering client-side
  • script to move all files from one location to another location
  • How to extract text from Word files using C#?
  • Trying to switch camera back to front but getting exception
  • what is the difference between the asp.net mvc application and asp.net web application
  • Timeout for blocking function call, i.e., how to stop waiting for user input after X seconds?
  • Matrix multiplication with MKL
  • Error creating VM instance in Google Compute Engine
  • Free memory of cv::Mat loaded using FileStorage API
  • Angular 2 constructor injection vs direct access
  • How does Linux kernel interrupt the application?
  • Programmatically clearing map cache
  • Running Map reduces the dimensions of the matrices
  • Binding checkboxes to object values in AngularJs