Databases
StackOverflow2013
Postsdbo
POMultiple objects somehow interfering with each other [original version]
 

Note that there are some explanatory texts on larger screens.

plurals
  1. POMultiple objects somehow interfering with each other [original version]
    primarykey
    data
    text
    <p>I have a neural network (NN) which works perfectly when applied to a single data set. However if I want to run the NN on, for example, one set of data and then create a new instance of the NN to run on different set of data (or even the same set again) then the new instance will produce completely incorrect predictions.</p> <p>For example, training on an XOR pattern:</p> <pre><code> test=[[0,0],[0,1],[1,0],[1,1]] data = [[[0,0], [0]],[[0,1], [0]],[[1,0], [0]],[[1,1], [1]]] n = NN(2, 3, 1) # Create a neural network with 2 input, 3 hidden and 1 output nodes n.train(data,500,0.5,0) # Train it for 500 iterations with learning rate 0.5 and momentum 0 prediction = np.zeros((len(test))) for row in range(len(test)): prediction[row] = n.runNetwork(test[row])[0] print prediction # # Now do the same thing again but with a new instance and new version of the data. # test2=[[0,0],[0,1],[1,0],[1,1]] data2 = [[[0,0], [0]],[[0,1], [0]],[[1,0], [0]],[[1,1], [1]]] p = NN(2, 3, 1) p.train(data2,500,0.5,0) prediction2 = np.zeros((len(test2))) for row in range(len(test2)): prediction2[row] = p.runNetwork(test2[row])[0] print prediction2 </code></pre> <p>Will output:</p> <pre><code> [-0.01 -0. -0.06 0.97] [ 0. 0. 1. 1.] </code></pre> <p>Notice that the first prediction is quite good where as the second is completely wrong, and I can't see anything wrong with the class: </p> <pre><code> import math import random import itertools import numpy as np random.seed(0) def rand(a, b): return (b-a)*random.random() + a def sigmoid(x): return math.tanh(x) def dsigmoid(y): return 1.0 - y**2 class NN: def __init__(self, ni, nh, no): # number of input, hidden, and output nodes self.ni = ni + 1 # +1 for bias node self.nh = nh + 1 self.no = no # activations for nodes self.ai = [1.0]*self.ni self.ah = [1.0]*self.nh self.ao = [1.0]*self.no # create weights (rows=number of features, columns=number of processing nodes) self.wi = np.zeros((self.ni, self.nh)) self.wo = np.zeros((self.nh, self.no)) # set them to random vaules for i in range(self.ni): for j in range(self.nh): self.wi[i][j] = rand(-5, 5) for j in range(self.nh): for k in range(self.no): self.wo[j][k] = rand(-5, 5) # last change in weights for momentum self.ci = np.zeros((self.ni, self.nh)) self.co = np.zeros((self.nh, self.no)) def runNetwork(self, inputs): if len(inputs) != self.ni-1: raise ValueError('wrong number of inputs') # input activations for i in range(self.ni-1): #self.ai[i] = sigmoid(inputs[i]) self.ai[i] = inputs[i] # hidden activations for j in range(self.nh-1): sum = 0.0 for i in range(self.ni): sum = sum + self.ai[i] * self.wi[i][j] self.ah[j] = sigmoid(sum) # output activations for k in range(self.no): sum = 0.0 for j in range(self.nh): sum = sum + self.ah[j] * self.wo[j][k] self.ao[k] = sigmoid(sum) ao_simplified = [round(a,2) for a in self.ao[:]] return ao_simplified def backPropagate(self, targets, N, M): if len(targets) != self.no: raise ValueError('wrong number of target values') # calculate error terms for output output_deltas = [0.0] * self.no for k in range(self.no): error = targets[k]-self.ao[k] output_deltas[k] = dsigmoid(self.ao[k]) * error # calculate error terms for hidden hidden_deltas = [0.0] * self.nh for j in range(self.nh): error = 0.0 for k in range(self.no): error = error + output_deltas[k]*self.wo[j][k] hidden_deltas[j] = dsigmoid(self.ah[j]) * error # update output weights for j in range(self.nh): for k in range(self.no): change = output_deltas[k]*self.ah[j] self.wo[j][k] = self.wo[j][k] + N*change + M*self.co[j][k] self.co[j][k] = change #print N*change, M*self.co[j][k] # update input weights for i in range(self.ni): for j in range(self.nh): change = hidden_deltas[j]*self.ai[i] self.wi[i][j] = self.wi[i][j] + N*change + M*self.ci[i][j] self.ci[i][j] = change # calculate error error = 0.0 for k in range(len(targets)): error = error + 0.5*(targets[k]-self.ao[k])**2 return error def train(self, patterns, iterations=1000, N=0.5, M=0.1): # N: learning rate # M: momentum factor for i in range(iterations): error = 0.0 for p in patterns: inputs = p[0] targets = p[1] self.runNetwork(inputs) error = error + self.backPropagate(targets, N, M) if i % 100 == 0: # Prints error every 100 iterations print('error %-.5f' % error) </code></pre> <p>Any help would be greatly appreciated! </p>
    singulars
    1. PO
      singulars
      1. PTAnswer
    1. This table or related slice is empty.
    1. PTQuestion
    1. USiRoygbiv
    1. USiRoygbiv
    plurals
    1. This table or related slice is empty.
    1. PL
      singulars
      1. LTLinked
    2. PL
      singulars
      1. LTDuplicate
    1. This table or related slice is empty.
    1. PO
      singulars
      1. PTAnswer
    1. This table or related slice is empty.
    1. COHow can we know what's wrong with your `NN` class without seeing the code? I suspect you've used a class variable instead of an instance variable, but it's impossible to tell.
      singulars
      1. POMultiple objects somehow interfering with each other [original version]
      1. USDaniel Roseman
    2. COI am still learning, hence: "I've not added the NN class code yet as It's pretty long and I hope that the cause of the problem might be obvious to those who know more than me." If it's not obvious though, then I will post it.
      singulars
      1. POMultiple objects somehow interfering with each other [original version]
      1. USiRoygbiv
    3. COThis may be of interest: http://sscce.org/
      singulars
      1. POMultiple objects somehow interfering with each other [original version]
      1. USMarcin
 

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